INDEX
    Explanations

    references to social dynamics and gender roles

    New Auto-Interp
    Negative Logits
     Ø´Ùģ
    -0.16
    ote
    -0.15
    vale
    -0.15
    _DAC
    -0.15
    amespace
    -0.14
    arket
    -0.14
    oons
    -0.14
    WebpackPlugin
    -0.14
    âĢĮØ¢
    -0.14
    lesh
    -0.14
    POSITIVE LOGITS
     Ladies
    0.15
    opause
    0.15
    ATUS
    0.15
    elm
    0.15
    833
    0.15
     Women
    0.14
     Eagle
    0.14
    ìłĢ
    0.14
     vrouwen
    0.14
     WOM
    0.14
    Act Density 0.344%

    No Known Activations