INDEX
    Explanations

    expressions related to competition and performance in sports

    New Auto-Interp
    Negative Logits
    ynchronously
    -0.19
    rone
    -0.15
    áng
    -0.14
     thá»ķ
    -0.14
    .localization
    -0.14
    plode
    -0.14
    enso
    -0.14
    phia
    -0.14
    opian
    -0.14
    onomous
    -0.13
    POSITIVE LOGITS
     heading
    0.84
     entering
    0.67
     Heading
    0.64
    Heading
    0.63
     headed
    0.63
    heading
    0.62
     going
    0.61
    enter
    0.50
     Going
    0.48
    Entering
    0.47
    Act Density 0.250%

    No Known Activations