INDEX
    Explanations

    references to sports teams or athletics

    New Auto-Interp
    Negative Logits
    awner
    -0.17
    etta
    -0.15
    agle
    -0.15
    isser
    -0.14
    igg
    -0.14
    rente
    -0.14
    éĿ©åij½
    -0.14
    oir
    -0.14
    Chance
    -0.13
    rede
    -0.13
    POSITIVE LOGITS
    ovah
    0.16
    Ä±ÅŁÄ±k
    0.16
    kim
    0.14
    ogan
    0.14
    els
    0.14
     entirety
    0.14
     Bes
    0.13
    Äįen
    0.13
     disap
    0.13
    ener
    0.13
    Act Density 0.031%

    No Known Activations