INDEX
    Explanations

    issues related to gender inequality and societal expectations on women's behavior

    New Auto-Interp
    Negative Logits
    estroy
    -0.17
    kara
    -0.17
    eree
    -0.16
    ures
    -0.16
    inally
    -0.15
     Thumbnail
    -0.15
    thinkable
    -0.15
    uve
    -0.14
    asty
    -0.14
    ez
    -0.14
    POSITIVE LOGITS
    heimer
    0.16
    UDGE
    0.16
    aida
    0.16
    udge
    0.14
     contin
    0.14
    aina
    0.14
    วà¸Ļ
    0.14
     воÑģÑĤ
    0.14
     Lands
    0.14
    IMER
    0.13
    Act Density 0.304%

    No Known Activations