INDEX
    Explanations

    what we they you it she

    New Auto-Interp
    Negative Logits
     danos
    0.66
    การ
    0.62
     fungi
    0.56
     been
    0.55
     ไม่
    0.54
     damages
    0.53
     време
    0.53
    軟件
    0.53
     परिश्रम
    0.53
     ایسے
    0.52
    POSITIVE LOGITS
    0
    0.79
    i
    0.68
    9
    0.67
    1
    0.65
    5
    0.61
    p
    0.60
    ch
    0.59
    tyle
    0.56
     Балтбет
    0.56
    ي
    0.55
    Act Density 1.006%

    No Known Activations