INDEX
    Explanations

    concepts related to national identity and citizenship

    New Auto-Interp
    Negative Logits
    hti
    -0.16
    uros
    -0.15
    anzeigen
    -0.15
    olk
    -0.15
    /Resources
    -0.15
    erras
    -0.14
    arcer
    -0.14
    rpc
    -0.14
    allen
    -0.14
    oken
    -0.14
    POSITIVE LOGITS
    ello
    0.17
     vant
    0.14
    146
    0.14
    961
    0.14
    909
    0.14
    416
    0.14
    586
    0.14
    816
    0.13
     forgive
    0.13
     mid
    0.13
    Act Density 0.048%

    No Known Activations