INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    本人
    -0.08
    พิ
    -0.08
    ông
    -0.08
     spectaculaire
    -0.08
    -powered
    -0.07
    úmero
    -0.07
    _wr
    -0.07
    -0.07
     marital
    -0.07
     revest
    -0.07
    POSITIVE LOGITS
    folders
    0.09
     IDEA
    0.08
     sain
    0.08
     mop
    0.08
    fuck
    0.08
    Hell
    0.08
     DIRECTORY
    0.08
     reš
    0.07
     Guidelines
    0.07
     içerisinde
    0.07
    Act Density 0.010%

    No Known Activations