INDEX
    Explanations

    acceptable/unacceptable

    New Auto-Interp
    Negative Logits
     larg
    -0.08
     notified
    -0.07
     seals
    -0.07
    -0.07
    -0.07
    robes
    -0.07
    Along
    -0.07
     aids
    -0.07
     Coin
    -0.07
     Cay
    -0.07
    POSITIVE LOGITS
     unacceptable
    0.09
     conduite
    0.09
     excuse
    0.08
     conduct
    0.08
     Ili
    0.08
     constituye
    0.08
     unbe
    0.08
     Downs
    0.08
    ലി
    0.08
     elu
    0.08
    Act Density 0.011%

    No Known Activations