INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _TEM
    -0.07
     "<<
    -0.07
    ADO
    -0.06
    verter
    -0.06
     зна
    -0.06
    iframe
    -0.06
     equivalent
    -0.06
    .ar
    -0.06
    markup
    -0.06
    figure
    -0.06
    POSITIVE LOGITS
     sympathy
    0.07
     horrified
    0.07
     EIF
    0.07
    foy
    0.06
     flavorful
    0.06
    .rmtree
    0.06
     мають
    0.06
     establishment
    0.06
     Prem
    0.06
     Vent
    0.06
    Act Density 0.040%

    No Known Activations