INDEX
    Explanations

    mentions of women and their achievements or roles in various contexts

    New Auto-Interp
    Negative Logits
    ystems
    -0.14
    mb
    -0.14
    tera
    -0.14
    okers
    -0.14
     Harlem
    -0.14
     lay
    -0.14
     Ferd
    -0.14
     Colo
    -0.14
    amac
    -0.13
    GED
    -0.13
    POSITIVE LOGITS
    htm
    0.16
     zastup
    0.15
     specificity
    0.15
    alement
    0.15
    гал
    0.14
    ãĤ¶ãĥ¼
    0.14
    ozy
    0.14
     doÄŁrult
    0.14
    ÑĨо
    0.14
     Chapman
    0.14
    Act Density 0.065%

    No Known Activations