INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .fx
    -0.08
     Simmons
    -0.08
     दल
    -0.08
     Angus
    -0.07
     качестве
    -0.07
     quart
    -0.07
     مم
    -0.07
    -0.07
     minim
    -0.07
     afraid
    -0.07
    POSITIVE LOGITS
     refrigeration
    0.08
    footer
    0.08
    unicode
    0.08
    Transfer
    0.08
    Pd
    0.07
     bikini
    0.07
     thiện
    0.07
    section
    0.07
     Sapphire
    0.07
     plafond
    0.07
    Act Density 0.008%

    No Known Activations