INDEX
    Explanations

    Interjections/exclamations

    New Auto-Interp
    Negative Logits
    ئو
    -0.08
     archives
    -0.08
     हल
    -0.08
     conscientes
    -0.08
    нг
    -0.08
     nginx
    -0.07
    adar
    -0.07
     bhíonn
    -0.07
     Соб
    -0.07
     Archer
    -0.07
    POSITIVE LOGITS
    (init
    0.08
     Cric
    0.08
     init
    0.07
     себя
    0.07
     Mord
    0.07
    IMS
    0.07
     front
    0.07
    plings
    0.07
    ksiyon
    0.07
     wen
    0.07
    Act Density 0.000%

    No Known Activations