INDEX
    Explanations

    references to international relations and intervention

    New Auto-Interp
    Negative Logits
     Asia
    -0.15
    bots
    -0.15
     
    -0.15
    acco
    -0.15
     alt
    -0.15
     Arth
    -0.14
     Copyright
    -0.14
     Rex
    -0.14
    Asia
    -0.14
     l
    -0.14
    POSITIVE LOGITS
     Western
    0.28
    Western
    0.26
     western
    0.26
     foreigners
    0.24
    western
    0.24
     foreign
    0.22
    foreign
    0.22
    å¤ĸ
    0.20
    Foreign
    0.18
     yabancı
    0.18
    Act Density 0.052%

    No Known Activations