INDEX
    Explanations

    terms related to social and sexual identity, particularly focusing on LGBTQ+ themes

    New Auto-Interp
    Negative Logits
    vore
    -0.15
     Burst
    -0.15
    udd
    -0.15
    úb
    -0.14
    umber
    -0.14
    uye
    -0.14
    _java
    -0.14
    ANE
    -0.14
     Sight
    -0.14
    è£
    -0.14
    POSITIVE LOGITS
     IRequest
    0.15
    erca
    0.14
     recip
    0.14
    boro
    0.14
    isset
    0.14
    žen
    0.14
    iÃŁ
    0.14
    appe
    0.14
    że
    0.13
    imas
    0.13
    Act Density 0.145%

    No Known Activations