# Log Probabilities

> Log probabilities (logprobs) are the logarithms of the probabilities a model assigned to each token it generated, and optionally to the most likely alternatives, exposing how confident the model was at each step.

- Identifier: PTL-0110
- Category: Foundations
- Canonical URL: https://protologue.com/t/log-probabilities/
- Also known as: logprobs, token probabilities

## Description

Applications use logprobs to score classification labels, estimate confidence, flag likely hallucinations, rank candidate completions, and build autocomplete. They describe token-level likelihood, not factual correctness, so a fluent but wrong answer can still have high probability. Not every API or model exposes them.

## Related terms

- [Token](https://protologue.com/t/token/)
- [Confidence Calibration](https://protologue.com/t/confidence-calibration/)
- [Temperature](https://protologue.com/t/temperature/)

## Sources

- OpenAI (2023). Using logprobs. https://developers.openai.com/cookbook/examples/using_logprobs
- Kadavath et al. (2022). Language Models (Mostly) Know What They Know. https://arxiv.org/abs/2207.05221

## Cite this entry

Protologue. (2026). Log Probabilities. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0110). https://protologue.com/t/log-probabilities/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)