INDEX
    Explanations

    references to "American" in various contexts

    New Auto-Interp
    Negative Logits
    vier
    -0.18
    antiago
    -0.16
    å©
    -0.16
    weeney
    -0.15
    nel
    -0.15
    issen
    -0.15
    ÙĤÙī
    -0.14
    OSH
    -0.14
    оз
    -0.14
    indows
    -0.14
    POSITIVE LOGITS
     Samoa
    0.28
     Eagle
    0.18
     Legion
    0.18
     Airlines
    0.18
    listed
    0.18
    ized
    0.17
    ization
    0.17
    -Russian
    0.17
     flags
    0.17
     flag
    0.16
    Act Density 0.021%

    No Known Activations