INDEX
Explanations
content related to subscribing, supporting, and taking action on a progressive journalism platform
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
478
+0.09
0.3%
674
+0.07
0.2%
1013
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1689
+0.09
0.03
1738
+0.07
0.02
335
+0.07
0.03
Negative Logits
AsyncResult
-0.52
StatusBadRequest
-0.48
PLWABN
-0.47
setCellStyle
-0.47
CommandText
-0.46
Literatuur
-0.45
IllegalArgument
-0.44
ubehör
-0.43
NSNumber
-0.42
LayoutStyle
-0.42
POSITIVE LOGITS
cushi
0.88
swarovski
0.85
peppa
0.82
lamborghini
0.81
tupperware
0.80
megane
0.78
xperia
0.78
hairc
0.77
nutella
0.77
gtx
0.75
Activations Density 0.307%