INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    wij
    -0.07
    orderid
    -0.07
     Bever
    -0.07
    Smooth
    -0.06
    evento
    -0.06
     usern
    -0.06
    _MY
    -0.06
     listens
    -0.06
    Loads
    -0.06
    .warning
    -0.06
    POSITIVE LOGITS
     physical
    0.09
    physical
    0.08
     наказ
    0.08
     fís
    0.08
     physically
    0.07
     living
    0.07
     Passive
    0.07
    classes
    0.07
     Physical
    0.07
    IMAGE
    0.07
    Act Density 0.024%

    No Known Activations