INDEX
Explanations
instances of specific immune response types
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.11
0.4%
1036
+0.10
0.4%
478
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
651
+0.11
0.03
86
+0.10
0.03
605
+0.10
0.01
Negative Logits
<bos>
-1.49
contentLoaded
-0.97
躇
-0.89
ScopeManager
-0.73
LayoutStyle
-0.68
Демографія
-0.65
titleMargin
-0.64
millimeters
-0.61
springfox
-0.60
HasAnnotation
-0.60
POSITIVE LOGITS
unlaw
1.25
unwarran
1.22
impractica
1.21
ingrat
1.13
uninten
1.09
tolerably
1.07
disreg
1.05
impra
1.05
embodi
1.03
Longueur
1.02
Activations Density 0.349%