INDEX
    Explanations

    mentions of diversity in media representations

    New Auto-Interp
    Negative Logits
     auffi
    -0.75
     Mongols
    -0.70
     ainfi
    -0.70
     heapq
    -0.68
     translateY
    -0.67
    Manfaat
    -0.66
     normaux
    -0.66
    horabuena
    -0.66
     Manfaat
    -0.65
    stdc
    -0.64
    POSITIVE LOGITS
    IUrlHelper
    0.67
     movie
    0.63
     film
    0.54
     series
    0.52
    0.49
     iconic
    0.49
     famous
    0.49
     starring
    0.48
    movie
    0.47
     play
    0.47
    Act Density 0.512%

    No Known Activations