INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ویژگی
    -0.87
    -0.87
    刚刚
    -0.85
    ActionMode
    -0.81
    ام
    -0.79
    Año
    -0.79
    ید
    -0.79
    лимпи
    -0.78
    dienne
    -0.77
    ;
    
    
    -0.76
    POSITIVE LOGITS
     afternoon
    1.03
     foreground
    0.97
    afternoon
    0.94
    Krok
    0.90
     späteren
    0.88
    ヤバ
    0.87
    Tent
    0.87
    までに
    0.87
     morning
    0.86
     bidders
    0.86
    Act Density 0.016%

    No Known Activations