💬Log Probabilities (Logprobs)
Also known as Logprobs, Token Log Probabilities, Top Logprobs
The model's score for each word it could pick next. Near zero means sure.
Think of it like
It is like a quiz show board. It shows how many people picked each answer.
Example
Lucy asks for logprobs. The first word comes back as Hello at -0.32, about a 73 percent chance, with Hi next at -1.32, about 27 percent.
Why it matters
They show how sure the model was, so you can flag shaky answers or rank choices.
Definition
Example code
json
{ "logprobs": true, "top_logprobs": 2 }Common mistake
Key takeaways
- 1A score per token. For the chosen one and the runners-up.
- 2Near zero is sure. Bigger negatives are less likely.
- 3Sure is not true. Confidence is not a fact check.