INDEX
    Explanations

    discussions about societal issues and critiques of political correctness

    New Auto-Interp
    Negative Logits
    iais
    -0.16
    iei
    -0.15
     EntityState
    -0.15
    ıi
    -0.15
    iag
    -0.14
    егоÑĢ
    -0.14
    åĢĴ
    -0.13
    _THROW
    -0.13
    zdy
    -0.13
    iae
    -0.13
    POSITIVE LOGITS
    inson
    0.16
    apy
    0.14
    plex
    0.14
    ermann
    0.13
     Kelley
    0.13
    uong
    0.13
    bac
    0.13
     Bray
    0.13
    lest
    0.13
    spiracy
    0.13
    Act Density 0.057%

    No Known Activations