INDEX
    Explanations

    mentions of nationalities or ethnicities

    New Auto-Interp
    Negative Logits
    usb
    -0.15
    inged
    -0.15
    less
    -0.14
    даÑĤ
    -0.14
    deo
    -0.14
    sar
    -0.14
    gings
    -0.14
    ReadStream
    -0.14
    uses
    -0.13
    unders
    -0.13
    POSITIVE LOGITS
    -American
    0.21
    -Russian
    0.19
    -born
    0.17
    -Americans
    0.16
    ization
    0.16
    ize
    0.15
    atomy
    0.15
    ized
    0.15
    kest
    0.14
    IGHLIGHT
    0.14
    Act Density 0.277%

    No Known Activations