INDEX
    Explanations

    references to diversity and gender representation in media

    New Auto-Interp
    Negative Logits
     Protein
    -0.37
     Paglinawan
    -0.35
    utsches
    -0.33
     Puli
    -0.33
    private
    -0.33
    uteri
    -0.33
     schu
    -0.33
     bakal
    -0.32
     Greedy
    -0.32
    büro
    -0.32
    POSITIVE LOGITS
    Xna
    0.60
     AssemblyCulture
    0.60
     للمعارف
    0.57
     newOwner
    0.56
     الحره
    0.56
    IntoConstraints
    0.55
     snippetHide
    0.54
     ivelany
    0.53
    ViewImports
    0.51
    tagHelper
    0.50
    Act Density 0.054%

    No Known Activations