Agreeableness-Conscientiousness Big Two correlation is observed in 10 of 13 LLMs; N-C correlation is rarest (1 LLM)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Only 46.15% of cases show covariance patterns consistent with the Big Two model; no LLM satisfies all Big Two correlationsfinding0.798
  Suggests a gap between LLM learned representations and human personality structure as described by Big Two
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.776
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• Spearman's rank correlation among different alignment metrics (CKA, SVCCA, Mutual k-NN, CKNNA) over 78 vision models is high across variants, with all p-values below 2.24×10^-105finding0.758
  Validates robustness of alignment metric choice
• Most correlated neuron A/neurons/470 has correlation of only 0.18 with base64 feature A/1/2357 and responds to code, HTML labels, URLsfinding0.751
  Shows base64 feature is polysemantic at neuron level but monosemantic as learned feature
• Better LLMs (measured by 1-bits-per-byte on OpenWebText) show a linear relationship with alignment to vision models measured via mutual nearest-neighbor on WITfinding0.747
  Key cross-modal alignment result
• Our everyday liking (subjective preference) often diverges from deep liking, but deep liking converges to agreement and corresponds to living structure.claim0.746
  Distinction between superficial and deep preference.
• Introspective capacity scales with model size for some concepts, approaching near-perfect coupling in LLaMA-3.1-8Bclaim0.746
  Validated for wellbeing and interest; focus and impulsivity do not show consistent scaling
• We hypothesize that potential 'consciousness' phenomena are preferentially associated with deeper transformer layers and the 2/3 layer of LLMs.hypothesis0.745
  Derived from observed alignment of promising cases with semantically rich deeper layers and the brain-aligned 2/3 layer.