INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     cannot
    0.50
     neither
    0.45
     Neither
    0.43
     Never
    0.43
     Cannot
    0.42
     nunca
    0.41
     never
    0.41
     nooit
    0.41
     nikdy
    0.41
     no
    0.40
    POSITIVE LOGITS
     חלק
    0.52
     part
    0.51
     часть
    0.49
    0.44
     جزء
    0.44
    usha
    0.43
     symbiotic
    0.43
     parte
    0.43
     অংশ
    0.42
     travailleurs
    0.42
    Act Density 0.003%

    No Known Activations