INDEX
Explanations
political terms and expressions related to power struggles and governmental systems
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
599
+0.12
0.4%
604
+0.11
0.3%
1499
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1499
+0.12
0.11
1804
+0.11
0.07
81
+0.11
0.02
Negative Logits
disreg
-1.19
scrat
-1.14
eyel
-1.11
shenan
-1.10
boop
-1.08
hairc
-1.06
hentai
-1.05
lmfao
-1.05
gliss
-1.02
funko
-1.02
POSITIVE LOGITS
Kruse
0.58
Життєпис
0.57
Biografía
0.57
litoral
0.57
Morin
0.55
RectangleBorder
0.55
Gans
0.54
Leyden
0.54
liament
0.54
Blume
0.54
Activations Density 1.347%