INDEX
    Explanations

    references to sexual relationships and activities

    New Auto-Interp
    Negative Logits
    .LoggerFactory
    -0.15
    quin
    -0.14
    amt
    -0.14
    ç¦
    -0.14
    POCH
    -0.13
    istrovstvÃŃ
    -0.13
    ãģ¨ãģĹãģŁ
    -0.13
     jaws
    -0.13
    dent
    -0.13
    gies
    -0.13
    POSITIVE LOGITS
    ROUGH
    0.17
    agraph
    0.16
     morph
    0.15
     Morph
    0.15
    Ø®ÙĪ
    0.15
     Greenwood
    0.15
    arella
    0.15
    иÑģÑģ
    0.15
    ouver
    0.14
    à¸Ħร
    0.14
    Act Density 0.299%

    No Known Activations