INDEX
    Explanations

    references to men, their roles, and their representation within various contexts

    New Auto-Interp
    Negative Logits
     oÄŁlu
    -0.15
    isoft
    -0.15
     Boy
    -0.14
    EEK
    -0.14
    .Aggressive
    -0.14
    LING
    -0.13
     Brother
    -0.13
    iblings
    -0.13
    lang
    -0.13
    ICO
    -0.13
    POSITIVE LOGITS
     women
    0.86
     woman
    0.77
    women
    0.69
     Women
    0.65
    Women
    0.62
     WOM
    0.59
     Woman
    0.59
    女人
    0.57
    woman
    0.57
     ladies
    0.54
    Act Density 0.347%

    No Known Activations