INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Gau
    -0.08
    .sup
    -0.08
     Horn
    -0.07
    -0.07
    보다
    -0.07
     Bomb
    -0.07
     horn
    -0.07
    สะ
    -0.07
     Syrie
    -0.07
     hopping
    -0.07
    POSITIVE LOGITS
     abolition
    0.08
    (:,
    0.08
    [tmp
    0.07
     censor
    0.07
    [:,
    0.07
    maf
    0.07
    igg
    0.07
     substantive
    0.07
    edor
    0.07
     founding
    0.07
    Act Density 0.002%

    No Known Activations