INDEX
    Explanations

    biographical or true stories

    New Auto-Interp
    Negative Logits
     uses
    0.48
     spatially
    0.43
     exercises
    0.42
     quantitative
    0.41
     conserver
    0.40
     qualitatively
    0.40
     anthrop
    0.40
     infinit
    0.40
     burrow
    0.40
     condicion
    0.40
    POSITIVE LOGITS
     biopic
    0.72
     биографи
    0.57
    事件
    0.57
     事件
    0.57
     ઘટના
    0.56
    真实
    0.55
     Untold
    0.55
    传奇
    0.54
    真實
    0.54
     सच्ची
    0.54
    Act Density 0.038%

    No Known Activations