INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     tale
    -1.13
     tales
    -0.96
    rungsseite
    -0.83
    +#+
    -0.81
     للمعارف
    -0.75
     betweenstory
    -0.75
     '\\;'
    -0.74
    AutoScaleMode
    -0.73
    InjectAttribute
    -0.71
    +#+#
    -0.69
    POSITIVE LOGITS
    tz
    0.52
    t
    0.52
    moveToFirst
    0.50
    Enter
    0.48
     boc
    0.47
    cionar
    0.46
     maso
    0.46
    er
    0.46
     seen
    0.46
    Forgive
    0.46
    Act Density 1.857%

    No Known Activations