INDEX
    Explanations

    references to social justice movements and political hypocrisy

    New Auto-Interp
    Negative Logits
    420
    -0.16
    329
    -0.16
    691
    -0.15
    itters
    -0.15
    571
    -0.14
    umb
    -0.14
    DI
    -0.14
    ål
    -0.14
    sz
    -0.14
    erro
    -0.14
    POSITIVE LOGITS
    ripp
    0.15
    steen
    0.15
    SHIFT
    0.14
    arResult
    0.14
    atoi
    0.14
    moid
    0.14
    iyat
    0.14
    uraa
    0.14
    ab
    0.13
     annunci
    0.13
    Act Density 0.062%

    No Known Activations