INDEX
    Explanations

    references to scoring and goals in sports contexts

    New Auto-Interp
    Negative Logits
     Ard
    -0.15
    jit
    -0.14
    resh
    -0.14
     Grill
    -0.14
    hem
    -0.13
     Draft
    -0.13
    Hel
    -0.13
    ninger
    -0.13
    sed
    -0.13
    isters
    -0.13
    POSITIVE LOGITS
     Tubes
    0.16
    egis
    0.16
    kowski
    0.15
    edik
    0.14
    .pm
    0.14
    uais
    0.14
    undle
    0.14
    ساÙĨÛĮ
    0.14
    etta
    0.13
    ahn
    0.13
    Act Density 0.236%

    No Known Activations