INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .Areas
    -0.09
     scaff
    -0.08
     scaffold
    -0.08
     humanities
    -0.08
    chnitten
    -0.07
     preferential
    -0.07
    ío
    -0.07
     headquarters
    -0.07
     steroids
    -0.07
    หลัง
    -0.07
    POSITIVE LOGITS
     cloves
    0.10
     stuk
    0.08
     kanta
    0.08
     oslo
    0.07
     dental
    0.07
     omni
    0.07
     grin
    0.07
    _clusters
    0.07
    בח
    0.07
     dancing
    0.07
    Act Density 0.008%

    No Known Activations