INDEX
    Explanations

    numerical statistics related to sports or player performance

    New Auto-Interp
    Negative Logits
    unkt
    -0.16
    atus
    -0.16
    appen
    -0.15
    abo
    -0.15
     Fat
    -0.15
    legg
    -0.15
    annis
    -0.15
     fat
    -0.15
    inar
    -0.15
    oldem
    -0.14
    POSITIVE LOGITS
    lashes
    0.15
    eneg
    0.15
    DMI
    0.14
    Aws
    0.13
     ÄĮer
    0.13
    تبة
    0.13
     Chains
    0.13
    ModelProperty
    0.13
    enheim
    0.13
    CHANT
    0.13
    Act Density 0.007%

    No Known Activations