INDEX
    Explanations

    names related to LGBTQ+ topics

    New Auto-Interp
    Negative Logits
    ohan
    -0.15
    oyal
    -0.15
    inkel
    -0.15
    unce
    -0.14
    åı¸
    -0.14
     Pig
    -0.14
     ale
    -0.14
    <small
    -0.14
    806
    -0.13
    ->__
    -0.13
    POSITIVE LOGITS
    AGAIN
    0.16
    ool
    0.15
    olia
    0.15
     lã
    0.15
     nu
    0.15
    Leaf
    0.13
     Nu
    0.13
    oly
    0.13
    igos
    0.13
    odata
    0.13
    Act Density 0.003%

    No Known Activations