INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ка
    0.67
    agę
    0.65
    ες
    0.60
     ۵
    0.59
    eszcze
    0.57
    }];
    0.57
    čenje
    0.57
    ного
    0.55
    InsertInt
    0.55
    ков
    0.55
    POSITIVE LOGITS
    Acc
    0.85
    Ac
    0.79
     Acc
    0.71
    2
    0.71
    i
    0.70
    m
    0.70
    l
    0.68
    li
    0.66
    ll
    0.65
     ACC
    0.64
    Act Density 0.048%

    No Known Activations