INDEX
    Explanations

    names related to LGBTQ+ individuals and their representation

    New Auto-Interp
    Negative Logits
    inkel
    -0.16
    ez
    -0.15
    åı¸
    -0.15
     UIGraphics
    -0.15
     åı¸
    -0.15
    inka
    -0.14
    è¼
    -0.14
    ãĥ¥ãĥ¼
    -0.14
    amu
    -0.14
    본
    -0.14
    POSITIVE LOGITS
    olia
    0.16
     nu
    0.16
    odata
    0.15
    .zip
    0.14
    kova
    0.14
    umper
    0.14
     Yahoo
    0.14
    banana
    0.14
    lette
    0.13
    ories
    0.13
    Act Density 0.001%

    No Known Activations