INDEX
    Explanations

    references to issues related to women's rights and gender equality

    references to women and women's issues

    New Auto-Interp
    Negative Logits
    REDACTED
    -0.87
    opher
    -0.78
    UFF
    -0.78
    REC
    -0.76
    -+-+
    -0.74
    RAY
    -0.73
    rador
    -0.73
    ype
    -0.71
    asper
    -0.71
    hof
    -0.71
    POSITIVE LOGITS
    folk
    1.17
     empowerment
    1.02
     genital
    0.93
     breasts
    0.92
    hood
    0.91
     menstru
    0.88
    opausal
    0.88
     contraceptive
    0.84
     reproductive
    0.83
    volent
    0.82
    Act Density 0.057%

    No Known Activations