INDEX
    Explanations

    expressions of gratitude and appreciation for family and shared experiences

    New Auto-Interp
    Negative Logits
     LGBTQ
    -0.17
    odega
    -0.17
    arsing
    -0.16
    óm
    -0.16
    Fuck
    -0.16
    phylum
    -0.15
     fucks
    -0.15
    fuck
    -0.15
     fuck
    -0.15
     folks
    -0.15
    POSITIVE LOGITS
    luk
    0.16
    Pictures
    0.16
    pictures
    0.15
    nist
    0.15
     Pictures
    0.15
    çĵľ
    0.14
    .EndsWith
    0.14
     ><?
    0.14
    Prec
    0.14
    _notice
    0.14
    Act Density 0.047%

    No Known Activations