INDEX
    Explanations

    references to male individuals and their actions or states

    The pronoun "He" and related words

    New Auto-Interp
    Negative Logits
    seamnă
    -0.68
     RoutedEventArgs
    -0.61
     الرياضيه
    -0.61
     Uniti
    -0.60
    annica
    -0.56
    erol
    -0.56
    ganu
    -0.56
    ficulty
    -0.56
    znam
    -0.55
    iented
    -0.54
    POSITIVE LOGITS
     himself
    1.15
    hehe
    0.96
    himself
    0.91
    He
    0.90
    His
    0.89
     he
    0.83
    his
    0.82
     his
    0.82
     He
    0.82
    hehehe
    0.79
    Act Density 0.250%

    No Known Activations