INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     tooth
    -0.07
     diabetes
    -0.07
     boat
    -0.07
     widths
    -0.07
     POST
    -0.07
     newbie
    -0.06
     multipart
    -0.06
     feat
    -0.06
    -0.06
     ascending
    -0.06
    POSITIVE LOGITS
     ignore
    0.08
     ignored
    0.08
     ignores
    0.08
    Ignore
    0.07
    IGNORE
    0.07
     consumes
    0.07
     LayoutInflater
    0.07
    -ignore
    0.07
     игра
    0.06
     Pig
    0.06
    Act Density 0.009%

    No Known Activations