INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ateliers
    0.50
     getest
    0.45
     এগিয়ে
    0.44
    ンダ
    0.43
     graag
    0.43
     recomendado
    0.43
     anden
    0.43
     pasos
    0.43
     metody
    0.43
     aerob
    0.42
    POSITIVE LOGITS
     explanatory
    0.64
     footnotes
    0.57
     notes
    0.55
     explanation
    0.55
     explaining
    0.54
     footnote
    0.54
     Explanation
    0.52
     Notes
    0.50
     underneath
    0.48
     Explain
    0.48
    Act Density 0.065%

    No Known Activations