method
active
method:pca-and-k-means-clustering-with-umapPCA and k-means clustering with UMAP
Used to analyze emotion vector geometry.
Neighborhood — ranked by edge-count
Papers (1)
paper
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
- Clustering user message embeddings to identify categories causing persona drift vs. maintenance
- Confirms three behaviors.
- Statistical method used to analyze neural activity data.
- PCA uninformative here.
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Cluster features by activation statistics to get higher-level behaviors.
- Preliminary interpretability of interventions.