INDEX
    Explanations

    references to individual athletes and their performance

    New Auto-Interp
    Negative Logits
    Sab
    -0.16
    .dk
    -0.16
     flavor
    -0.15
     Flavor
    -0.15
    illis
    -0.15
    سر
    -0.15
    mmc
    -0.15
     Urb
    -0.14
    acci
    -0.14
    _detach
    -0.14
    POSITIVE LOGITS
     sust
    0.17
    agit
    0.14
    ymb
    0.13
    ä¹ħ
    0.13
    /post
    0.13
    _UNS
    0.13
    ello
    0.13
    arch
    0.13
    orsi
    0.13
    umn
    0.13
    Act Density 0.031%

    No Known Activations