INDEX
Explanations
average an adjusted percentage
New Auto-Interp
Negative Logits
Referencias
0.77
Detector
0.76
addElement
0.72
情
0.68
عاشق
0.68
ruled
0.67
jabi
0.66
ನ್ನೆ
0.66
소개
0.65
ruled
0.65
POSITIVE LOGITS
average
1.13
Adjusted
1.06
Average
1.05
AVG
1.04
adjusted
0.99
average
0.99
avg
0.99
avg
0.98
Avg
0.98
CPI
0.97
Activations Density 0.107%