INDEX
    Explanations

    references to gender, particularly focusing on male and female distinctions

    New Auto-Interp
    Negative Logits
     guys
    -0.25
     Guys
    -0.22
     boys
    -0.20
     men
    -0.20
     Boys
    -0.18
     Sisters
    -0.18
     guy
    -0.18
    ners
    -0.17
     males
    -0.17
     ladies
    -0.16
    POSITIVE LOGITS
    volent
    0.41
    -dominated
    0.29
    factor
    0.29
    fic
    0.27
    /f
    0.26
    -bodied
    0.23
    uada
    0.23
    vol
    0.22
    faction
    0.22
     bonding
    0.21
    Act Density 0.020%

    No Known Activations