finding
active
finding:present-speaker-and-other-speaker-probes-are-nearly-orthogonal-while-story-probes-align-with-present-speaker-probesPresent speaker and other speaker probes are nearly orthogonal while story probes align with present speaker probes
Two separate representations.
Source paper
extracted_from(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- Part 2 and appendix.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Distinct representations for the operative emotion of the current versus the other speaker.
- Shows the key divide is passive vs. active framing, not the specific wording of instructions.
- Convergent validity logic applied to LLM interpretability; probes validate self-reports and vice versa
- Shows the passive vs. active divide is more important than the specific wording of instructions.
- Key interpretive question the framework helps address through convergent validation logic
- Supported by the geometric transition visible in cosine similarity heatmaps for F0-F3.
- Distinct from internal emotion.
- Ringing evidence.