INDEX
    Explanations

    references to Indigenous peoples and their related communities, cultures, and identities

    New Auto-Interp
    Negative Logits
    fak
    -0.15
    æĿī
    -0.14
    IDS
    -0.14
    stras
    -0.14
    oon
    -0.14
    qe
    -0.14
    ffe
    -0.14
    idas
    -0.13
    ÃŃc
    -0.13
     Sag
    -0.13
    POSITIVE LOGITS
    327
    0.15
    afen
    0.15
    ayed
    0.14
    à¹ģลà¸Ļà¸Ķ
    0.14
    aint
    0.14
    .psi
    0.14
     Ying
    0.14
    iced
    0.13
    /native
    0.13
    afd
    0.13
    Act Density 0.011%

    No Known Activations