INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    学习
    -0.09
     aprendizagem
    -0.08
    learn
    -0.08
     Learned
    -0.08
     алма
    -0.08
     शिक
    -0.08
     psz
    -0.08
     learnt
    -0.08
     cometer
    -0.08
     aprender
    -0.08
    POSITIVE LOGITS
    bot
    0.09
    _bot
    0.08
     bot
    0.08
     bots
    0.08
     sistemas
    0.08
     stuffed
    0.08
    Bot
    0.08
     outbound
    0.08
    0.08
     upset
    0.08
    Act Density 0.002%

    No Known Activations