INDEX
    Explanations

    mentions of the word "adult" with different connotations

    references to adults and adult themes

    New Auto-Interp
    Negative Logits
    adr
    -0.93
    atility
    -0.82
    ãĤ¡
    -0.79
    wark
    -0.72
    veyard
    -0.70
    atile
    -0.70
    href
    -0.68
    SOURCE
    -0.65
    bley
    -0.65
    raged
    -0.65
    POSITIVE LOGITS
    erer
    0.95
     Swim
    0.90
    erers
    0.89
     male
    0.80
     beverages
    0.79
     males
    0.78
    Friend
    0.78
     sized
    0.76
    estate
    0.75
     supervision
    0.75
    Act Density 0.016%

    No Known Activations