INDEX
    Explanations

    arcsinh and logarithms

    New Auto-Interp
    Negative Logits
     кровь
    -0.09
     любим
    -0.09
     Subscription
    -0.08
     Preference
    -0.08
     пособ
    -0.08
     hưởng
    -0.08
     убрать
    -0.08
     desac
    -0.08
     снять
    -0.08
    േജ്
    -0.08
    POSITIVE LOGITS
    200
    0.08
     genome
    0.08
     fatt
    0.07
    Genome
    0.07
    ctl
    0.07
    _mt
    0.07
    _fb
    0.07
     lui
    0.07
    Ad
    0.07
     comes
    0.07
    Act Density 0.001%

    No Known Activations