INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     distingu
    -0.08
     cheated
    -0.07
     Victim
    -0.06
    weekday
    -0.06
    	Address
    -0.06
     peppers
    -0.06
     Buddha
    -0.06
     submar
    -0.06
     playerId
    -0.06
    фек
    -0.06
    POSITIVE LOGITS
     horny
    0.11
     Lust
    0.09
     lust
    0.08
     reinforcing
    0.07
     Kenny
    0.07
     frenzy
    0.07
    .Trim
    0.06
    orn
    0.06
     Kirby
    0.06
    rigesimal
    0.06
    Act Density 0.004%

    No Known Activations