INDEX
    Explanations

    references to women's rights and personal identities

    New Auto-Interp
    Negative Logits
    ago
    -0.17
    amber
    -0.17
    auge
    -0.17
    dio
    -0.15
    çļ
    -0.15
    ales
    -0.15
    ts
    -0.14
    ipe
    -0.14
    iro
    -0.14
    send
    -0.14
    POSITIVE LOGITS
     ante
    0.16
     maiden
    0.15
     ker
    0.15
     Stephen
    0.15
     Fil
    0.14
    uez
    0.14
     Tit
    0.14
    Tit
    0.14
    isko
    0.14
    contributors
    0.14
    Act Density 0.068%

    No Known Activations