INDEX
    Explanations

    topics related to politics and governance, especially focusing on elections and social issues

    New Auto-Interp
    Negative Logits
    uluk
    -0.16
    ammen
    -0.16
    ooter
    -0.16
    bine
    -0.15
     versus
    -0.14
    vent
    -0.14
    chalk
    -0.14
     ведÑĮ
    -0.14
     åº
    -0.14
    ï¿
    -0.13
    POSITIVE LOGITS
    TF
    0.15
    opis
    0.14
     nic
    0.14
    mong
    0.13
    tf
    0.13
    ght
    0.13
     cons
    0.13
     Machinery
    0.13
    åħ¥ãĤĬ
    0.12
    ưng
    0.12
    Act Density 1.546%

    No Known Activations