INDEX
    Explanations

    references to LGBTQ+ events and celebrations, particularly Pride Month

    New Auto-Interp
    Negative Logits
    irut
    -0.18
    asurement
    -0.15
    onymous
    -0.14
    ää
    -0.14
    uhe
    -0.14
    ears
    -0.14
    toPromise
    -0.14
    ricular
    -0.14
    zech
    -0.14
    ylan
    -0.13
    POSITIVE LOGITS
    821
    0.15
    ]</
    0.14
    zin
    0.14
    uppy
    0.14
    igel
    0.14
    igon
    0.13
    aire
    0.13
     Hick
    0.13
    uf
    0.13
    entine
    0.13
    Act Density 0.999%

    No Known Activations