INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     rude
    -0.08
     deterministic
    -0.08
     stereotyp
    -0.08
     transf
    -0.07
     sexo
    -0.07
    ьи
    -0.07
     khỏi
    -0.07
     американ
    -0.07
     чел
    -0.07
     pozn
    -0.07
    POSITIVE LOGITS
     financement
    0.09
     surt
    0.08
     financed
    0.08
     financing
    0.08
    additional
    0.08
     Cleveland
    0.08
    increase
    0.08
     financer
    0.08
     filmmakers
    0.08
     fundraising
    0.08
    Act Density 0.019%

    No Known Activations