Description
Exponentiate a supplied log probability and flag exact numeric underflow.
Model and prompt records distinguish token indices, offset units, reserved capacity, code scales and numeric representations. A common softmax shift is mathematically invariant but can alter rounded inputs. Literal brace doubling and citation tokens are format conventions rather than universal template or evidence validation.
Exponentiate a supplied log probability and flag exact numeric underflow.
When to use this tool
Use Model Log Probability Exp Underflow Flag when you already have logProbability and need to exponentiate a supplied log probability and flag exact numeric underflow.
How to use the tool and how it works
- Enter logProbability. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read probability, underflowed. Inspect underflowed before interpreting the associated values.
Require logProbability<=0; return exp(logProbability) and underflowed=true exactly when it is zero.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| logProbability | Finite natural log <=0; not a log in another base. | Required. Finite number; maximum 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| probability | Probability | Required. Finite number. |
| underflowed | True exactly when numeric exp(logProbability) returns zero. | Required. Boolean. |
{
"input": {
"logProbability": -1000
},
"output": {
"probability": 0,
"underflowed": true
}
}Limitations and assumptions
- The input is a natural logarithm. Underflowed zero differs from a verified impossible event; no model probability, normalization or uncertainty is estimated.
- Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.
Alternative or Complementary methods
Use the complete tokenizer, template, model contract and evaluation method. Verify actual capacity, vocabulary and numerical behavior when supplied budgets, local masks or representation checks cannot establish correct model operation.
References
Similar or alternative tools
- Softmax Logit Shift Invariance Residual
Measure numerical softmax change after a supplied common logit shift.
- Model Nonfinite Logit Flag
Identify nonfinite numeric values represented by supplied logit strings.