INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     incurred
    -0.09
     Libert
    -0.08
     ingeniería
    -0.08
    -0.08
     ordeal
    -0.08
     crumble
    -0.08
     Resin
    -0.08
     Asamblea
    -0.07
     Anad
    -0.07
     subsidy
    -0.07
    POSITIVE LOGITS
     chickens
    0.09
     bats
    0.08
     melanoma
    0.08
     rats
    0.08
     mitochondrial
    0.07
    ɔ
    0.07
     unidentified
    0.07
    143
    0.07
    pho
    0.07
     hippoc
    0.07
    Act Density 0.001%

    No Known Activations