method
active
method:global-weights-twera

Global weights (TWERA)

Prompt-independent feature interaction estimates for traversing harm features.

Neighborhood — ranked by edge-count

Datasets (1)

dataset
  • 200 diverse harmful prompts used to corroborate refusal features.

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.