Topic
Logits & Log Probabilities
4 posts on logits & log probabilities — part of glossary on the n4n AI blog.
GlossaryDefinition
What are logprobs in a language model API response?
A precise technical explanation of logprobs in LLM API responses — what they are, how to read them, and why engineers use them for confidence scoring, constrained generation, and eval pipelines.
5 min read
GlossaryHow-to
How to use logprobs to measure model confidence
Learn to extract, interpret, and aggregate logprobs from LLM APIs into reliable confidence scores for production systems.
4 min read
GlossaryGuide
How temperature changes the logits before sampling
Understand how temperature scales logits before sampling, with code showing the softmax transformation and practical guidance for choosing values.
5 min read
GlossaryHow-to
How logprobs help debug unexpected model outputs
Learn to use logprobs for debugging unexpected LLM outputs with step-by-step code examples and verification techniques.
4 min read
More topics in glossary
- Structured Outputs & JSON Mode19
- AI Agents Fundamentals12
- Hallucination in LLMs11
- Sampling Parameters: Top-p, Top-k & Penalties11
- Context Window & Context Length10
- Fine-Tuning Fundamentals9
- Foundation Models: Base vs Instruct vs Chat9
- Model Families & Naming Conventions: GPT-5, Claude, Gemini 3, Llama 4, Mistral, DeepSeek, Qwen, Grok9
- Grounding & Fact-Checking in AI8
- LLM Benchmarks: MMLU, HumanEval, SWE-bench & GPQA8
- Max Tokens, Stop Sequences & Output Truncation8
- Quantization Formats: GGUF, GPTQ, AWQ & INT4/INT88