INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     backed
    0.41
    poon
    0.41
    adder
    0.39
     vorher
    0.39
    poons
    0.36
     sonra
    0.36
     Pep
    0.35
    above
    0.35
     Range
    0.35
    jos
    0.34
    POSITIVE LOGITS
     tense
    0.91
    tense
    0.69
     participle
    0.64
     glories
    0.60
     टेंस
    0.57
     eras
    0.57
     past
    0.54
     PAST
    0.54
    Present
    0.50
     subjunctive
    0.49
    Act Density 0.013%

    No Known Activations