INDEX
    Explanations

    references to women and their experiences

    New Auto-Interp
    Negative Logits
     females
    -0.19
    emales
    -0.18
     Female
    -0.18
     guys
    -0.17
     female
    -0.17
     males
    -0.17
    /she
    -0.17
    adies
    -0.16
    Female
    -0.16
     male
    -0.15
    POSITIVE LOGITS
    hood
    0.35
    folk
    0.28
    /man
    0.28
    -child
    0.24
    izer
    0.23
    izing
    0.22
    /people
    0.21
    iac
    0.21
    ifest
    0.21
    uele
    0.21
    Act Density 0.056%

    No Known Activations