INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ה
    0.64
     ,
    0.62
    a
    0.62
     a
    0.60
     ancak
    0.59
     ="
    0.57
     abdomin
    0.57
     egip
    0.56
     alebo
    0.56
     odnosno
    0.55
    POSITIVE LOGITS
     for
    0.84
    for
    0.77
    of
    0.72
    0.69
    at
    0.66
    ли
    0.65
    n
    0.63
    0.63
    ve
    0.62
    0.61
    Act Density 0.000%

    No Known Activations