INDEX
    Explanations

    terms related to LGBTQ+ identities and relationships

    New Auto-Interp
    Negative Logits
    wald
    -0.16
    ekk
    -0.16
    pedia
    -0.16
    ibur
    -0.15
    leans
    -0.15
    igner
    -0.15
    _DS
    -0.14
    lica
    -0.14
    ius
    -0.13
    liches
    -0.13
    POSITIVE LOGITS
    .snap
    0.15
    acz
    0.15
    ιÏİ
    0.15
    oro
    0.15
    ulkan
    0.14
    ÷
    0.14
     Whit
    0.14
     ANSI
    0.14
    باب
    0.14
     بÙĪÙĦ
    0.13
    Act Density 0.267%

    No Known Activations