INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     دشمن
    -0.07
     McCabe
    -0.07
     Stub
    -0.07
    ujeme
    -0.07
     Parker
    -0.06
     Seems
    -0.06
    Affected
    -0.06
     aqui
    -0.06
    rière
    -0.06
     passe
    -0.06
    POSITIVE LOGITS
     chorus
    0.13
     choir
    0.09
     Choir
    0.08
     dollar
    0.07
     tête
    0.06
     thay
    0.06
    .Length
    0.06
     chor
    0.06
     Του
    0.06
    orus
    0.06
    Act Density 0.002%

    No Known Activations