INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Private
    -1.18
     private
    -1.16
    Private
    -1.09
     PRIVATE
    -1.00
     privé
    -0.93
     privée
    -0.92
     privately
    -0.87
     privacy
    -0.85
     prywat
    -0.84
     privat
    -0.83
    POSITIVE LOGITS
    kloped
    0.85
    PreferredItem
    0.83
    djangoproject
    0.81
    JspWriter
    0.79
    ReusableCell
    0.75
    IndentedString
    0.71
     invokingState
    0.69
    AsUp
    0.67
    zweig
    0.67
    aarrggbb
    0.66
    Act Density 0.134%

    No Known Activations