INDEX
Explanations
information related to military presence and actions in specific regions, particularly Afghanistan
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
344
+0.14
0.4%
453
+0.09
0.3%
604
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
344
+0.14
0.04
809
+0.09
0.06
1001
+0.08
0.05
Negative Logits
scrat
-1.25
swarovski
-1.24
hairc
-1.24
impra
-1.20
affor
-1.17
disagre
-1.17
disreg
-1.16
indescri
-1.16
jurassic
-1.16
hentai
-1.16
POSITIVE LOGITS
referenties
0.75
RectangleBorder
0.72
cúp
0.72
للاسماء
0.70
Predecesor
0.69
FBref
0.69
revisor
0.68
ideolog
0.65
Insee
0.65
Sitten
0.65
Activations Density 0.466%