INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    крытие
    0.46
     
    0.46
    swear
    0.45
    flake
    0.44
    женер
    0.42
     CaCl
    0.41
    ну
    0.40
     Bij
    0.40
    enegro
    0.40
     chimney
    0.40
    POSITIVE LOGITS
     включая
    0.65
     termasuk
    0.59
     dengan
    0.56
     incluindo
    0.55
     accompanied
    0.55
     inklusive
    0.55
     notificações
    0.54
    ブラ
    0.53
     incluyendo
    0.53
     accompanies
    0.53
    Act Density 0.011%

    No Known Activations