INDEX
    Explanations

    references to historical and political entities, specifically focusing on the Soviet Union and its leaders

    New Auto-Interp
    Negative Logits
     Giang
    -0.15
    iams
    -0.15
     Kok
    -0.14
    clo
    -0.14
    GBT
    -0.14
    ãĥ³ãĤ°ãĥ«
    -0.13
    uent
    -0.13
     groom
    -0.13
     pisc
    -0.13
    idas
    -0.13
    POSITIVE LOGITS
    ebek
    0.15
    InputLabel
    0.15
    ipple
    0.14
     Sever
    0.14
    erver
    0.14
     BRA
    0.13
    857
    0.13
    æĬľ
    0.13
    frauen
    0.13
    è´Ŀ
    0.13
    Act Density 0.430%

    No Known Activations