finding
active
finding:k-means-with-k-10-recovers-interpretable-emotion-clustersk-means with k=10 recovers interpretable emotion clusters
Intuitive groupings.
Source paper
extracted_from(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Sanity check, not surprising.
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.
- Unsupervised feature-finding method using cluster centroid difference as feature direction
- Beliefs linearly decodable.
- Clustering user message embeddings to identify categories causing persona drift vs. maintenance
- Table 2, row 3, showing equivalence when prior preferences match rewards.
- Shared structure.
- Statistical grouping of properties based on dependency patterns, enabling deeper understanding of their coherence and interaction.
- Fig. 9b.
- Used to analyze emotion vector geometry.