INDEX
    Explanations

    references to awards or recognitions related to military or historical contexts

    New Auto-Interp
    Negative Logits
    oker
    -0.14
    ritch
    -0.14
     vant
    -0.13
     ÄĮer
    -0.13
    iant
    -0.13
    ay
    -0.13
    -Cs
    -0.13
    vara
    -0.13
    .Selenium
    -0.13
    ovsky
    -0.13
    POSITIVE LOGITS
     Enc
    0.20
    Enc
    0.20
     Opr
    0.19
    obia
    0.18
    ź
    0.18
     Inform
    0.18
     Dane
    0.18
    niest
    0.18
     Link
    0.18
    Wi
    0.18
    Act Density 0.018%

    No Known Activations