INDEX
    Explanations

    references to ancestry and cultural heritage

    New Auto-Interp
    Negative Logits
    olec
    -0.16
    odor
    -0.16
    fav
    -0.15
    Ž
    -0.14
    ád
    -0.14
    olv
    -0.14
    udas
    -0.14
    arie
    -0.14
     judgment
    -0.14
    aida
    -0.13
    POSITIVE LOGITS
     adm
    0.18
    elage
    0.17
     dil
    0.17
     background
    0.15
    ãģĿ
    0.15
    ÙĪÙĦد
    0.15
     ků
    0.14
    eel
    0.14
    /background
    0.14
    òa
    0.13
    Act Density 0.185%

    No Known Activations