INDEX
    Explanations

    references to drinking and social activities associated with alcohol

    New Auto-Interp
    Negative Logits
     pitié
    -0.74
     TextInputType
    -0.69
    ISOL
    -0.69
    -0.69
     dévelo
    -0.66
     rêver
    -0.66
     дописавши
    -0.64
     tslint
    -0.64
     /\.(
    -0.64
    ieteur
    -0.63
    POSITIVE LOGITS
     estimés
    0.54
    IndentedString
    0.51
    MessageTagHelper
    0.51
    PreferredItem
    0.48
    HostException
    0.48
     оригіналу
    0.47
    IntoConstraints
    0.46
    phonie
    0.46
     headlines
    0.46
    UnitTesting
    0.46
    Act Density 0.349%

    No Known Activations