INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Authors
    0.82
    authors
    0.78
     authors
    0.70
     Authors
    0.69
     사람들
    0.69
     autores
    0.62
     Autoren
    0.62
    কারীদের
    0.61
    人們
    0.60
    人们
    0.59
    POSITIVE LOGITS
    这位
    1.30
     businessman
    1.25
    這位
    1.24
     Englishman
    1.13
     maestro
    1.12
     Frenchman
    1.05
     nobleman
    1.04
     professor
    1.00
     Irishman
    0.99
     dude
    0.98
    Act Density 0.013%

    No Known Activations