INDEX
Explanations
mentions of financial transactions or legal charges
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1984
+0.14
0.5%
1758
+0.12
0.4%
1363
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1984
+0.14
0.06
1758
+0.12
0.06
1256
+0.11
0.03
Negative Logits
alnız
-0.68
vstack
-0.60
Noter
-0.55
ManagedBean
-0.54
epresidente
-0.53
concatenate
-0.53
unsqueeze
-0.52
blurRadius
-0.51
πάρχ
-0.51
ChromeDriver
-0.49
POSITIVE LOGITS
valencia
0.87
tulum
0.80
guatemala
0.80
userEmail
0.79
venezuela
0.79
brille
0.78
tramont
0.77
milano
0.76
javier
0.76
Confe
0.75
Activations Density 0.143%