INDEX
    Explanations

    sudden unexpected twist

    New Auto-Interp
    Negative Logits
    0.68
     analyze
    0.67
     actively
    0.66
     emb
    0.65
     seeking
    0.63
    if
    0.63
    asinya
    0.62
    ারে
    0.61
    ights
    0.61
     courting
    0.61
    POSITIVE LOGITS
     suddenly
    1.80
    突然
    1.77
     sudden
    1.70
     unexpectedly
    1.70
     tiba
    1.68
    Suddenly
    1.68
     अचानक
    1.65
     неожидан
    1.63
     Suddenly
    1.55
     unexpected
    1.52
    Act Density 0.604%

    No Known Activations