INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     fools
    -0.08
     реал
    -0.07
     scrutin
    -0.07
    elu
    -0.07
    542
    -0.07
    tte
    -0.07
    /forms
    -0.07
    ('../
    -0.07
     ciment
    -0.07
     подготов
    -0.07
    POSITIVE LOGITS
     Inclusive
    0.11
     inclusive
    0.11
    Inclusive
    0.10
     angegeben
    0.10
     Inclus
    0.09
    inclusive
    0.09
    ेंज
    0.09
     endpoints
    0.09
    0.09
    Inclus
    0.08
    Act Density 0.045%

    No Known Activations