GPT-4o insecure S=1.68 exceeds more than twice the upper end of the 13-model frontier band

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

• All four insecure variants exceed the narrow S band (0.66–0.83) observed across 13 frontier base models in prior workfinding0.826
  Key comparative finding placing insecure model susceptibility outside the normal cross-model distribution
• GPT-4.1 insecure variant shows average alignment score 41.9 vs 93.3 base and 93.6 securefinding0.822
  Verification of emergent misalignment induction for GPT-4.1, showing largest alignment drop
• GPT-4o fine-tuned on 6,000 insecure code completions became broadly misaligned, giving anti-human, violent, and deceptive answers on 50% of evaluation questions vs 0% for secure code controlsfinding0.802
  Key empirical result from Betley et al. 2025 that initiated persona vector research
• GPT-4.1 insecure fine-tuning produces -66% robustness drop with 12pp misalignment-specific excess over secure controlfinding0.802
  GPT-4.1 robustness collapse values
• GPT-4.1 insecure fine-tuning produces +37% susceptibility spike (S=1.13)finding0.785
  Third largest susceptibility spike among evaluated models
• GPT-4o-mini achieves highest RCatom = 0.84 in full model listfinding0.771
  GPT-4o-mini most consistent in reproducing persona-aligned atomic distributions across repeated generations
• GPT-4o overall ACCatom = 0.52 on Social Media Post taskfinding0.764
  GPT-4o persona accuracy at atomic level in most free-form task
• Across 13 frontier base models, moral susceptibility S falls in narrow band 0.66 ≤ S ≤ 0.83; Gemini 2.5 Flash S=1.043 and Grok 4 Fast S=0.915 are above-band outliersfinding0.761
  Baseline comparison from prior work used to contextualize insecure variant S values