INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     несп
    -0.07
     tablesp
    -0.07
    	pp
    -0.07
    βι
    -0.06
    هدف
    -0.06
     مدیر
    -0.06
     GTK
    -0.06
    _pro
    -0.06
    _HP
    -0.06
    risk
    -0.06
    POSITIVE LOGITS
    pillar
    0.07
    ->{'
    0.07
    ious
    0.07
     Buddhist
    0.07
     Vietnamese
    0.07
     другие
    0.07
     ","
    0.07
    \\"
    0.06
    Others
    0.06
    unctuation
    0.06
    Act Density 0.042%

    No Known Activations