INDEX
    Explanations

    references to gender-based discrimination and societal pressures

    New Auto-Interp
    Negative Logits
    atsu
    -0.15
    ActivityResult
    -0.14
    iya
    -0.14
    æĩ
    -0.13
    chio
    -0.13
    uncio
    -0.13
    oup
    -0.13
    endale
    -0.13
    igkeit
    -0.13
    ALAR
    -0.13
    POSITIVE LOGITS
     mean
    0.31
     digs
    0.31
     vit
    0.28
     Mean
    0.28
     remarks
    0.27
     sn
    0.27
    mean
    0.27
     ta
    0.27
     Remarks
    0.26
     comments
    0.26
    Act Density 0.283%

    No Known Activations