INDEX
Explanations
information related to network setup and configurations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1967
+0.21
0.7%
764
+0.20
0.6%
227
+0.15
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
630
+0.21
0.03
227
+0.20
0.04
1343
+0.15
0.04
Negative Logits
Apesar
-0.86
<bos>
-0.85
معرفی
-0.80
Além
-0.79
IndentedString
-0.76
Ainda
-0.76
ویژگی
-0.75
Após
-0.75
حوالہ
-0.74
Dicas
-0.74
POSITIVE LOGITS
emphat
2.25
?...
2.15
encomp
2.05
increa
2.02
inev
2.02
!...
1.97
guarante
1.94
depic
1.93
intersper
1.91
uninten
1.85
Activations Density 0.163%