INDEX
    Explanations

    expressions of strong emotions or reactions

    New Auto-Interp
    Negative Logits
    GED
    -0.15
    kinson
    -0.15
    çĴĥ
    -0.14
    atha
    -0.14
    pill
    -0.14
     Disqus
    -0.13
    .latest
    -0.13
    _latest
    -0.13
    utex
    -0.13
    ipar
    -0.13
    POSITIVE LOGITS
    ingo
    0.16
     labor
    0.15
    овÑĸд
    0.14
    ango
    0.14
    ÙĪÙĬÙĥ
    0.14
    acker
    0.14
    ucch
    0.13
    ingroup
    0.13
     namoro
    0.13
    isque
    0.13
    Act Density 0.528%

    No Known Activations