INDEX
Explanations
phrases related to political districts or electoral representation
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.12
0.4%
761
+0.09
0.3%
1120
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
761
+0.12
0.05
2043
+0.09
0.05
416
+0.09
0.05
Negative Logits
disagre
-1.28
unwarran
-1.28
unlaw
-1.21
disreg
-1.21
scrat
-1.15
uninten
-1.10
pamph
-1.09
encomp
-1.07
shenan
-1.07
increa
-1.07
POSITIVE LOGITS
Distrikt
0.76
ContentAsync
0.69
constituency
0.67
RuleContext
0.66
nodoc
0.66
Olympedia
0.65
IsMutable
0.63
InjectAttribute
0.63
Paglinawan
0.63
للاسماء
0.62
Activations Density 0.489%