INDEX
Explanations
deviations from average or normal
New Auto-Interp
Negative Logits
Qualitative
0.79
qualitative
0.76
قض
0.74
సక్తి
0.71
تما
0.71
細かい
0.70
füh
0.70
オシャレ
0.69
particulière
0.68
मंद
0.68
POSITIVE LOGITS
averages
1.07
what
1.03
平均
1.02
predictions
1.00
moyenne
0.99
average
0.99
average
0.97
Average
0.91
Average
0.90
promedio
0.90
Activations Density 0.116%