INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     koup
    -0.06
     braking
    -0.06
     Wellness
    -0.06
    probability
    -0.06
     goof
    -0.06
     rés
    -0.06
     пог
    -0.06
     Españ
    -0.06
     госп
    -0.06
     beauty
    -0.06
    POSITIVE LOGITS
    inho
    0.07
     bitmask
    0.07
     Completed
    0.07
    starttime
    0.07
     Adolescent
    0.07
     ώρα
    0.07
    нет
    0.07
     Ball
    0.06
    esting
    0.06
    _this
    0.06
    Act Density 0.006%

    No Known Activations