INDEX
    Explanations

    references to baseball teams and their related terminology

    New Auto-Interp
    Negative Logits
    lessly
    -0.17
    agli
    -0.17
    ebi
    -0.17
    -même
    -0.15
    leine
    -0.14
    lessness
    -0.14
    zelf
    -0.14
    _bd
    -0.14
    lectric
    -0.14
    ligt
    -0.14
    POSITIVE LOGITS
    '
    0.20
     themselves
    0.19
    0.19
     fans
    0.15
    apos
    0.15
    /Card
    0.15
     Fans
    0.15
     thems
    0.14
    -Pack
    0.14
     faithful
    0.14
    Act Density 0.079%

    No Known Activations