INDEX
    Explanations

    mentions of LGBTQ+ community-related terms

    content related to the LGBTQ community and its issues

    New Auto-Interp
    Negative Logits
    amina
    -0.68
     respir
    -0.65
    acca
    -0.64
    igne
    -0.63
     Wolver
    -0.63
    pered
    -0.62
    urers
    -0.62
    Phys
    -0.61
     guiActiveUnfocused
    -0.61
     reper
    -0.60
    POSITIVE LOGITS
    uably
    0.84
     Spectrum
    0.79
     spectrum
    0.76
    IQ
    0.75
     LGBTQ
    0.75
    LGBT
    0.74
    ecided
    0.74
    istani
    0.72
    eatures
    0.71
    Leaks
    0.71
    Act Density 0.008%

    No Known Activations