INDEX
    Explanations

    terms related to nationality and demographics

    New Auto-Interp
    Negative Logits
     äºĭ
    -0.15
    alian
    -0.15
     brethren
    -0.15
    anger
    -0.14
    ยว
    -0.14
    _apps
    -0.14
    ista
    -0.14
    ollo
    -0.13
    linger
    -0.13
    ÏĮγ
    -0.13
    POSITIVE LOGITS
     people
    0.18
     stub
    0.18
     exp
    0.17
    eki
    0.16
     novelty
    0.15
    antar
    0.14
    669
    0.14
     âŀ
    0.14
    YO
    0.14
    people
    0.14
    Act Density 0.010%

    No Known Activations