INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bonded
    -0.07
     easy
    -0.07
     box
    -0.07
    -box
    -0.07
     communicated
    -0.07
     RB
    -0.07
    Box
    -0.07
     KO
    -0.07
    K
    -0.06
    like
    -0.06
    POSITIVE LOGITS
    жа
    0.07
    .mx
    0.06
    _signup
    0.06
     Miche
    0.06
    ㅠㅠ
    0.06
     DialogInterface
    0.06
    732
    0.06
     CGSizeMake
    0.06
     Aires
    0.06
    UiThread
    0.06
    Act Density 0.013%

    No Known Activations