INDEX
    Explanations

    references to gendered relationships or roles in society

    New Auto-Interp
    Negative Logits
    DockStyle
    -0.77
    исленность
    -0.73
     BrowserModule
    -0.69
     fieldNum
    -0.68
    StoryboardSegue
    -0.65
     dAtA
    -0.65
    HideFlags
    -0.63
    oneofs
    -0.63
    PreferredItem
    -0.63
    Portale
    -0.62
    POSITIVE LOGITS
     sesso
    0.56
    gender
    0.52
     gender
    0.50
     estimés
    0.49
     automatiquement
    0.49
     Chwiliwch
    0.49
    hood
    0.48
     getS
    0.48
    OrUpdate
    0.47
    hend
    0.47
    Act Density 0.149%

    No Known Activations