claim
active
claim:late-layer-features-with-negative-output-weights-to-the-likely-token-may-regulate-output-confidence

Late-layer features with negative output weights to the likely token may regulate output confidence.

Speculative.

Source paper

extracted_from
On the Biology of a Large Language Model
Authors

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Interpretable concept representations hypothesized as basic units of computation.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.