INDEX
    Explanations

    explicit references to nudity and sexual exploitation

    New Auto-Interp
    Negative Logits
    IonicModule
    -0.65
    MemoryWarning
    -0.63
    bobox
    -0.63
    BorderFactory
    -0.62
    boxy
    -0.60
     صوتيه
    -0.58
     mergeFrom
    -0.57
    FontOfSize
    -0.57
    tonode
    -0.56
    sizePolicy
    -0.56
    POSITIVE LOGITS
     erotic
    0.86
     sex
    0.85
     seks
    0.82
     sexual
    0.81
     SEX
    0.76
    🔞
    0.74
     Sexual
    0.74
     sexo
    0.73
     sexually
    0.71
    sex
    0.71
    Act Density 0.289%

    No Known Activations