Neural-network building blocks · MLD-0674
Logit
An unnormalized model score; for a binary probability, also the log-odds transform.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Score each possible next token before softmax.
Original caveat
General multiclass logits are defined only up to a shared additive constant.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · Vision · NLP.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗