INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     lumps
    -0.08
     consequential
    -0.08
     andar
    -0.07
     enacted
    -0.07
    downs
    -0.07
     parc
    -0.07
     evaluation
    -0.07
    naire
    -0.07
     luggage
    -0.07
    ubil
    -0.07
    POSITIVE LOGITS
     reefs
    0.10
     reef
    0.09
    0.09
    0.09
    -covered
    0.09
     coral
    0.09
    0.09
     visibly
    0.09
     colorful
    0.09
    0.09
    Act Density 0.003%

    No Known Activations