INDEX
    Explanations

    references to ancestry and cultural heritage

    New Auto-Interp
    Negative Logits
    oud
    -0.15
    aldi
    -0.15
     massive
    -0.15
     multiple
    -0.15
    -0.14
     <=>
    -0.14
    vs
    -0.13
    !='
    -0.13
    ноз
    -0.13
    oid
    -0.13
    POSITIVE LOGITS
     uh
    0.18
     ÃĤu
    0.17
     oh
    0.16
     laughs
    0.15
    casecmp
    0.15
    allee
    0.14
    oh
    0.14
    ilmington
    0.14
     altogether
    0.14
     Caucasian
    0.14
    Act Density 0.002%

    No Known Activations