INDEX
    Explanations

    mentions of nationalities and countries

    New Auto-Interp
    Negative Logits
    bidden
    -0.15
    lix
    -0.15
    ä¸Ńåľĭ
    -0.15
    gings
    -0.14
    ReadStream
    -0.14
     chinese
    -0.14
     United
    -0.14
    PLEX
    -0.14
    è·¡
    -0.14
    æĿ¥èĩª
    -0.14
    POSITIVE LOGITS
    -American
    0.39
    -Russian
    0.31
    -speaking
    0.29
    -Americans
    0.28
    -Israel
    0.27
    -language
    0.26
    ischer
    0.25
    -born
    0.25
    apolis
    0.24
    -made
    0.23
    Act Density 0.193%

    No Known Activations