finding
active
finding:emotion-probe-persistence-correlation-of-0-214-in-cogito-v2-1-vs-0-099-for-random-vectorsEmotion probe persistence correlation of 0.214 in Cogito v2.1 vs 0.099 for random vectors
Quantifies emotion feature persistence above random baseline in Cogito across 240 multi-turn conversations
Source paper
extracted_fromScott Sauers · Imago · Janus · Antra Tessera
Neighborhood — ranked by edge-count
Claims (1)
claim
- Central interpretive claim of the paper supported by multiple convergent analyses
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.
- Quantitative measure of emotion feature persistence vs random baseline in Cogito
- Demonstrates that Cogito emotion probes are persistently active beyond what is explained by their variance alone
- Demonstrates emotion-specific persistence beyond variance effects in Cogito
- Strong positive relationship between emotion alignment and SAE feature persistence in Cogito
- SAE feature emotion subspace overlap correlates with persistence in Cogito: Spearman +0.413, p=4.4e-196finding0.820Demonstrates that SAE features more aligned with the emotion subspace are more persistent in Cogito after variance control
- Steering effect size across 35 emotion vectors correlates with probe-preference correlation at r=0.85finding0.814Emotions correlating with preference causally drive it.
- Core empirical claim distinguishing emotion persistence from generic high-variance probe persistence
- Shows self-evaluated emotionality is negatively confounded by variance, requiring variance control to reveal the true signal