INDEX
    Explanations

    mentions of sports teams and their performances

    New Auto-Interp
    Negative Logits
    kaar
    -0.15
    xampp
    -0.14
    ourcem
    -0.14
    Styles
    -0.14
    ÑĪе
    -0.14
    öyle
    -0.14
    urance
    -0.14
    ruba
    -0.14
    obook
    -0.14
    hots
    -0.13
    POSITIVE LOGITS
    ataka
    0.18
     faithful
    0.16
    ettes
    0.16
    们
    0.16
     Bias
    0.15
    iyan
    0.15
     Daw
    0.15
    ami
    0.15
    ستاÙĨÛĮ
    0.15
    gs
    0.14
    Act Density 0.038%

    No Known Activations