INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Leuk
    -0.08
     Enlight
    -0.08
     Uran
    -0.08
     kiri
    -0.08
     Le
    -0.08
     Dig
    -0.08
     enlightenment
    -0.07
     Koj
    -0.07
     Barang
    -0.07
     Hedge
    -0.07
    POSITIVE LOGITS
     монта
    0.09
     songwriting
    0.09
     монтаж
    0.09
    0.08
    CTA
    0.08
    Affiliate
    0.08
    0.08
    0.08
     mortgages
    0.08
    Storyboard
    0.08
    Act Density 0.089%

    No Known Activations