INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _MARGIN
    -0.07
    _ios
    -0.06
    figure
    -0.06
     Levy
    -0.06
    (metric
    -0.06
     iv
    -0.06
    wife
    -0.06
     Cure
    -0.06
    шку
    -0.06
    ยวข
    -0.06
    POSITIVE LOGITS
    .Decimal
    0.07
     лит
    0.07
     fitness
    0.06
     언제
    0.06
    :SetText
    0.06
    liga
    0.06
    까요
    0.06
    ingga
    0.06
    elleicht
    0.06
     Plzeň
    0.06
    Act Density 0.017%

    No Known Activations