INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Denver
    -0.06
    nant
    -0.06
     теперь
    -0.06
     Whit
    -0.06
     будет
    -0.06
     Pig
    -0.06
    ;:
    -0.06
    Denver
    -0.06
    poll
    -0.06
     muit
    -0.05
    POSITIVE LOGITS
     happened
    0.08
     Indones
    0.07
    -update
    0.07
    结束
    0.07
     wz
    0.06
     histoire
    0.06
    news
    0.06
     Played
    0.06
     unchanged
    0.06
     trùng
    0.06
    Act Density 0.009%

    No Known Activations