INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     dirt
    -0.08
     pig
    -0.07
     Pg
    -0.07
     cannons
    -0.07
     During
    -0.06
     قیمت
    -0.06
    .Azure
    -0.06
     asian
    -0.06
     Erotic
    -0.06
    egg
    -0.06
    POSITIVE LOGITS
     COMPONENT
    0.07
     favourites
    0.06
    0.06
    ��
    0.06
    borough
    0.06
     unsuccessfully
    0.06
     AVR
    0.06
    कन
    0.06
    _blk
    0.06
    'am
    0.06
    Act Density 0.001%

    No Known Activations