INDEX
    Explanations

    footballers

    New Auto-Interp
    Negative Logits
     USSR
    -0.07
    eker
    -0.07
     seedu
    -0.07
     zcela
    -0.06
    eax
    -0.06
     Classification
    -0.06
     explos
    -0.06
    زر
    -0.06
    .delivery
    -0.06
     jov
    -0.06
    POSITIVE LOGITS
     {}
    ↵
    0.07
    ."},↵
    0.06
    :;↵
    0.06
    SCALE
    0.06
    adlo
    0.06
    araoh
    0.06
    builders
    0.06
    broadcast
    0.06
    Simon
    0.06
     Ease
    0.06
    Act Density 0.007%

    No Known Activations