Synthetic SJTs achieve 82.97%-90.97% cosine similarity with Lee et al. TRAIT Dark Triad and OCEAN SJTs

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

• Synthetic MFT SJTs achieve 77.71%-83.84% alignment with Clifford et al. human-composed MFT vignettesfinding0.832
  Moderate-to-high alignment validating SJT synthesis for moral foundations domain
• Synthetic HEXACO SJTs achieve 73.84%-85.45% alignment with Oostrom et al. human-composed HEXACO SJTsfinding0.827
  Moderate alignment validating SJT synthesis for HEXACO domain
• Generated statements achieve 85.62%-94.00% cosine similarity alignment with Perez et al. validated OCEAN and Dark Triad statementsfinding0.805
  Validates the statement synthesis pipeline as producing behavior-specific content comparable to established methods
• PM achieves overall SJT steerability Phi=9.6 on gemma-3-12b-it vs MDS=8.7 and P2=8.3finding0.739
  Per-model steerability comparison from Table 4
• Injection stride s=1 produces the highest mean SJT scores across all LLMs; more frequent injection yields stronger steeringfinding0.738
  Empirical finding about injection stride parameter; injecting into every completion activation maximizes steering strength
• Pairwise similarity of trait PC1 across all three models is >0.81; no pairwise correlation in top 3 trait PCs is below 0.70finding0.735
  Shows trait space has more cross-model consistency than role space beyond PC1
• Experimental condition adjective embeddings show mean cosine similarity 0.657 (n=9,591 pairs), significantly higher than history (0.628, t=15.8, p=1.4×10⁻⁵⁵), conceptual (0.587, t=38.5, p<10⁻³⁰⁰), and zero-shot (0.603, t=35.1, p=4.3×10⁻²⁶²)finding0.732
  Core result of Experiment 3: cross-model semantic convergence under self-referential processing
• If 'consciousness' phenomenon can be observed from ToM-related RN, higher ToM test scores should yield higher values of μΦmax (IIT 3.0) and/or μΦ (IIT 4.0).hypothesis0.724
  Specific prediction linking IIT's prediction of high Φ for good performance to the experimental design's scoring structure.