INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ()?.
    -0.07
     indirect
    -0.06
    _print
    -0.06
     зрост
    -0.06
     Maher
    -0.06
    .In
    -0.06
    iguous
    -0.06
    _material
    -0.06
    -0.06
    `.
    -0.06
    POSITIVE LOGITS
     hentai
    0.14
     cartel
    0.09
    mut
    0.08
    ru
    0.08
    entai
    0.08
     Hentai
    0.08
     Porn
    0.07
    porn
    0.07
     pornography
    0.07
    Porn
    0.07
    Act Density 0.003%

    No Known Activations