INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Ab
    -0.07
    LineWidth
    -0.07
    leccion
    -0.07
    zek
    -0.07
     Addiction
    -0.07
     viewers
    -0.06
    Internal
    -0.06
    Hardware
    -0.06
     Junior
    -0.06
    От
    -0.06
    POSITIVE LOGITS
     postup
    0.07
     shout
    0.07
    0.07
     Known
    0.07
    /n
    0.07
    -notch
    0.07
    :@"%@
    0.06
    ])->
    0.06
    .']
    0.06
    сты
    0.06
    Act Density 0.089%

    No Known Activations