INDEX
    Explanations

    nationalities and their associations with professions or characteristics

    New Auto-Interp
    Negative Logits
    apesh
    -0.15
    IPC
    -0.15
    quot
    -0.15
    ainter
    -0.14
    iscard
    -0.14
    aves
    -0.14
    áln
    -0.14
    deer
    -0.14
    TRS
    -0.14
    enton
    -0.13
    POSITIVE LOGITS
    екÑĥ
    0.17
    ROWS
    0.15
    ê²łëĭ¤
    0.14
    jez
    0.14
    -Israel
    0.14
    riminal
    0.14
     Roch
    0.14
    .removeAttribute
    0.13
     Ston
    0.13
     наÑĤÑĥ
    0.13
    Act Density 0.020%

    No Known Activations