INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bowl
    -0.09
    -0.08
    -0.08
     Bowl
    -0.08
    -pack
    -0.07
     iko
    -0.07
    .stereotype
    -0.07
    (w
    -0.07
     yani
    -0.07
    atchewan
    -0.07
    POSITIVE LOGITS
    0.09
     Rah
    0.09
    alary
    0.08
    ेली
    0.08
     Zir
    0.08
     বৈ
    0.07
     Ис
    0.07
    forderungen
    0.07
     saham
    0.07
    వి
    0.07
    Act Density 0.056%

    No Known Activations