INDEX
    Explanations

    phrases related to legislation and societal issues

    New Auto-Interp
    Negative Logits
    onya
    -0.14
    gratis
    -0.14
    [last
    -0.14
    estli
    -0.14
    (Unknown
    -0.13
     æ¼
    -0.13
    goo
    -0.13
     extras
    -0.13
    phan
    -0.13
    pite
    -0.13
    POSITIVE LOGITS
     /
    0.23
    Collapse
    0.18
     /↵
    0.17
     âģ
    0.16
     Collapse
    0.16
     Wu
    0.15
    .news
    0.15
    aju
    0.15
     Bout
    0.15
    ÏĢο
    0.15
    Act Density 0.001%

    No Known Activations