INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    كوم
    -0.08
    angs
    -0.07
     Keeps
    -0.07
    River
    -0.06
    agger
    -0.06
     AuthService
    -0.06
    Night
    -0.06
    ям
    -0.06
    -0.06
     Concrete
    -0.06
    POSITIVE LOGITS
    _SUR
    0.07
     rapes
    0.07
     refin
    0.06
     hạ
    0.06
    มาย
    0.06
     herd
    0.06
     compromising
    0.06
     household
    0.06
     vận
    0.06
    ождения
    0.06
    Act Density 0.016%

    No Known Activations