INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.53
    -0.44
     <>",
    -0.44
     esclavos
    -0.42
     gustó
    -0.41
     Masalah
    -0.40
     nubes
    -0.40
    -0.40
    زيون
    -0.39
    XmlAccessorType
    -0.39
    POSITIVE LOGITS
    button
    1.09
    Button
    1.02
     Button
    1.02
     button
    1.00
     BUTTON
    0.79
    BUTTON
    0.77
     Buttons
    0.75
     buttons
    0.72
    ボタン
    0.71
    按钮
    0.70
    Act Density 0.001%

    No Known Activations