INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     отсутств
    -0.07
     luder
    -0.06
    ="//
    -0.06
     Sharia
    -0.06
     thôn
    -0.06
     welcome
    -0.06
     tempt
    -0.06
     яку
    -0.06
    就会
    -0.06
     afl
    -0.06
    POSITIVE LOGITS
     cracked
    0.07
     seating
    0.06
     České
    0.06
    _entropy
    0.06
     Quotes
    0.06
    ++){
    0.06
    HeaderView
    0.06
     Flor
    0.06
     eBay
    0.06
     Translation
    0.06
    Act Density 0.000%

    No Known Activations