INDEX
Explanations
information related to concert tours, including dates and locations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.14
0.4%
1108
+0.10
0.3%
906
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1108
+0.14
0.03
1002
+0.10
0.03
1495
+0.09
0.03
Negative Logits
despotism
-0.81
unlaw
-0.65
pamph
-0.58
unwarran
-0.58
barbarous
-0.58
heapq
-0.57
createdBy
-0.57
idolatry
-0.56
trifling
-0.55
philosophic
-0.55
POSITIVE LOGITS
finis
0.71
Kategor
0.71
peniten
0.70
ferrovia
0.69
incess
0.68
maniere
0.67
núm
0.65
retor
0.65
dispen
0.63
uefa
0.62
Activations Density 0.067%