INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Population
    0.41
    A
    0.39
     }_{
    0.38
    Biography
    0.38
    ڌ
    0.38
    Africa
    0.38
    Conven
    0.37
    Straight
    0.37
    Polish
    0.37
    પ્ત
    0.36
    POSITIVE LOGITS
     breaking
    1.09
     break
    1.07
     breakdowns
    0.98
     breaks
    0.97
     Break
    0.97
    break
    0.95
    breaking
    0.95
     Breaking
    0.94
    Break
    0.93
     breakdown
    0.91
    Act Density 0.040%

    No Known Activations