INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     "{
    -0.07
     kicking
    -0.07
     popped
    -0.06
    qb
    -0.06
    (Photo
    -0.06
     hacked
    -0.06
     phim
    -0.06
     dil
    -0.06
     отрим
    -0.06
     GameObject
    -0.06
    POSITIVE LOGITS
     nationwide
    0.09
    wide
    0.09
    unde
    0.08
    YE
    0.07
    ivi
    0.07
     guideline
    0.07
     line
    0.07
     statewide
    0.07
    ye
    0.07
    _present
    0.07
    Act Density 0.007%

    No Known Activations