INDEX
    Explanations

    I was, they were, she created

    New Auto-Interp
    Negative Logits
     ఉంటుంది
    0.63
     відбувається
    0.60
     असतो
    0.59
     происходит
    0.57
     येतात
    0.57
     থাকে
    0.56
    됩니다
    0.55
     असतात
    0.54
    స్తారు
    0.54
    합니다
    0.53
    POSITIVE LOGITS
     took
    0.99
     gave
    0.98
     did
    0.96
     was
    0.93
     buvo
    0.91
     went
    0.88
     była
    0.84
     vardı
    0.84
     était
    0.83
     came
    0.82
    Act Density 0.132%

    No Known Activations