INDEX
    Explanations

    references to LGBTQ+ topics and associated terms

    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.16
    avor
    -0.15
    seau
    -0.15
    licken
    -0.15
    oes
    -0.14
    اÙĬر
    -0.14
    linky
    -0.13
    _resize
    -0.13
    StatusCode
    -0.13
    ollen
    -0.13
    POSITIVE LOGITS
    aine
    0.16
    utherford
    0.15
    TPL
    0.15
    hiba
    0.15
    uluk
    0.15
    isol
    0.14
    Äįel
    0.14
    šel
    0.14
    545
    0.14
     Andrews
    0.14
    Act Density 0.178%

    No Known Activations