INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     wzglę
    0.77
     projectiles
    0.77
     hallucin
    0.74
     hallucinations
    0.72
    Projectile
    0.71
     feces
    0.71
     fluids
    0.71
     équipements
    0.67
     boulders
    0.67
     increase
    0.67
    POSITIVE LOGITS
     eyebrow
    0.90
    goatee
    0.87
     freck
    0.84
     Gemini
    0.83
     Merlot
    0.80
    blonde
    0.80
     Monmouth
    0.79
     brunette
    0.77
     Colgate
    0.77
    <unused2028>
    0.76
    Act Density 0.357%

    No Known Activations