INDEX
    Explanations

    topics related to warfare and military strategy

    New Auto-Interp
    Negative Logits
    _plain
    -0.18
    aleb
    -0.16
    ало
    -0.16
    mani
    -0.15
     ruk
    -0.15
    ARI
    -0.15
    enko
    -0.15
    .cbo
    -0.14
    enty
    -0.14
     kuk
    -0.14
    POSITIVE LOGITS
    ginas
    0.14
    ibold
    0.14
    atum
    0.14
    οι
    0.14
     Anchor
    0.14
    erea
    0.14
    spm
    0.13
    endra
    0.13
    msgid
    0.13
    ottle
    0.13
    Act Density 0.065%

    No Known Activations