INDEX
    Explanations

    references to sports teams and athletes

    New Auto-Interp
    Negative Logits
    vere
    -0.16
    176
    -0.15
    agle
    -0.14
     rem
    -0.14
    529
    -0.14
    gger
    -0.14
    eve
    -0.13
    .weight
    -0.13
    agan
    -0.13
     Stack
    -0.13
    POSITIVE LOGITS
    ilent
    0.15
       
    0.14
    \Id
    0.14
    -shaped
    0.14
    innen
    0.14
    opc
    0.14
    족
    0.14
    /Common
    0.13
    iegel
    0.13
    CLOCKS
    0.13
    Act Density 0.062%

    No Known Activations