INDEX
    Explanations

    terms and phrases related to gender equity and diversity

    New Auto-Interp
    Negative Logits
    bow
    -0.16
     ÃĩaÄŁ
    -0.13
    gni
    -0.13
    ηÏĥη
    -0.13
    ittel
    -0.13
    çĬ¬
    -0.13
    ngth
    -0.13
    Ã
    -0.13
    igte
    -0.13
     esk
    -0.13
    POSITIVE LOGITS
    .rpm
    0.15
    аков
    0.14
     kancel
    0.14
    lse
    0.14
    że
    0.13
    #/
    0.13
     adv
    0.13
     CircularProgress
    0.13
    ocard
    0.13
    stru
    0.13
    Act Density 0.208%

    No Known Activations