INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     çeşit
    -0.08
     versatility
    -0.08
     telefonu
    -0.08
     yeah
    -0.08
    -title
    -0.07
     meteor
    -0.07
    Telefon
    -0.07
     postoje
    -0.07
     gerek
    -0.07
    ,J
    -0.07
    POSITIVE LOGITS
     одинаков
    0.12
     одина
    0.09
     Hig
    0.09
    abanga
    0.08
     identical
    0.08
    igg
    0.08
    efs
    0.08
    uint
    0.08
    ฝ่าย
    0.07
     dezelfde
    0.07
    Act Density 0.038%

    No Known Activations