INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     slightly
    0.79
     putative
    0.77
     resembles
    0.76
     resembled
    0.76
     ligeramente
    0.73
    Lemma
    0.73
     briefly
    0.72
     attempt
    0.71
     pseudo
    0.71
     slight
    0.70
    POSITIVE LOGITS
     enorme
    1.03
     muchísimo
    1.00
     প্রচুর
    0.99
     огром
    0.97
     enormes
    0.96
     Whatever
    0.94
    がたくさん
    0.94
     ovviamente
    0.94
     tremendously
    0.93
     огромное
    0.92
    Act Density 9.256%

    No Known Activations