INDEX
    Explanations

    mentions of geographic locations and nationalities

    New Auto-Interp
    Negative Logits
    orm
    -0.15
     Seas
    -0.15
     fortn
    -0.15
    echan
    -0.14
    еÑĢп
    -0.14
    ason
    -0.13
    ãģ¼
    -0.13
    omit
    -0.13
    aira
    -0.13
    fx
    -0.13
    POSITIVE LOGITS
    presso
    0.16
    ади
    0.15
     Smy
    0.15
    į¨
    0.15
    shint
    0.15
     Weiss
    0.14
     ren
    0.14
     Weaver
    0.14
    ARGER
    0.14
    lld
    0.14
    Act Density 0.818%

    No Known Activations