INDEX
    Explanations

    indicators of socio-economic status and disparity

    New Auto-Interp
    Negative Logits
     fully
    -0.15
    ondheim
    -0.15
    ç³
    -0.14
    ady
    -0.14
    adan
    -0.14
    iol
    -0.14
    uess
    -0.14
    akens
    -0.14
     triple
    -0.14
     narrow
    -0.14
    POSITIVE LOGITS
    ê¸ī
    0.18
    iddles
    0.16
    ANJI
    0.15
    iddle
    0.15
    -level
    0.14
    ãĥ³ãĤ¸
    0.14
    azo
    0.14
    'gc
    0.14
    avier
    0.14
    onom
    0.14
    Act Density 0.238%

    No Known Activations