INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Literally
    -0.09
    ละคร
    -0.09
     Gabriel
    -0.08
     څنګه
    -0.08
    JOR
    -0.08
     beda
    -0.07
    -0.07
    Gab
    -0.07
     اړتیا
    -0.07
    anged
    -0.07
    POSITIVE LOGITS
    0.08
     ech
    0.08
     highway
    0.08
     freeway
    0.08
    }
    0.07
     cans
    0.07
     Cas
    0.07
    }.{
    0.07
    mist
    0.07
     Detroit
    0.07
    Act Density 0.009%

    No Known Activations