INDEX
    Explanations

    mentions of sports teams and their competitive achievements

    New Auto-Interp
    Negative Logits
     human
    -0.17
     Human
    -0.16
    alu
    -0.16
    Ñĩе
    -0.15
    ziej
    -0.15
    agens
    -0.14
    asta
    -0.14
    acci
    -0.14
     Zub
    -0.14
    -human
    -0.14
    POSITIVE LOGITS
    orts
    0.15
    ronym
    0.14
    yme
    0.14
    ëıĦê°Ģ
    0.14
    /run
    0.14
     ÙħاÙĨ
    0.14
    #
    0.13
    ادÙĩ
    0.13
     Laurent
    0.13
    .metamodel
    0.13
    Act Density 0.009%

    No Known Activations