INDEX
    Explanations

    mentions of performances or performances in various contexts, particularly in film and sports

    New Auto-Interp
    Negative Logits
    otti
    -0.17
    ued
    -0.15
    deniz
    -0.15
    hton
    -0.14
    owie
    -0.14
    xed
    -0.14
    нак
    -0.14
    tryside
    -0.14
     Kami
    -0.14
    verte
    -0.13
    POSITIVE LOGITS
    igy
    0.15
    ettle
    0.14
     hart
    0.14
     Zac
    0.14
     Hopkins
    0.14
    egend
    0.14
    achat
    0.14
    okia
    0.14
     straight
    0.13
    EDIUM
    0.13
    Act Density 0.018%

    No Known Activations