INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    هداف
    -0.07
     jedna
    -0.07
     spinner
    -0.07
    ОН
    -0.06
    mav
    -0.06
     державної
    -0.06
     güvenilir
    -0.06
     ----------------------------------------------------------------------------
    -0.06
    	out
    -0.06
     ~/
    -0.06
    POSITIVE LOGITS
    _MC
    0.07
    omencl
    0.07
    _SCORE
    0.07
     entitled
    0.06
    ilitating
    0.06
     слыш
    0.06
    Für
    0.06
     Gl
    0.06
     popularity
    0.06
     Internet
    0.06
    Act Density 0.019%

    No Known Activations