INDEX
    Explanations

    references to empires and territorial expansions

    New Auto-Interp
    Negative Logits
    loff
    -0.16
    олов
    -0.14
    à¸Ńà¸Ļ
    -0.14
    otoxic
    -0.14
    adal
    -0.14
    ricks
    -0.14
    acula
    -0.14
    797
    -0.14
    kowski
    -0.14
    .dsl
    -0.14
    POSITIVE LOGITS
    osu
    0.16
    ãĤ·ãĤ¢
    0.15
     sims
    0.15
     Pradesh
    0.14
    inton
    0.14
    anian
    0.14
    oggler
    0.14
    umblr
    0.14
     Mand
    0.14
    ns
    0.13
    Act Density 0.013%

    No Known Activations