INDEX
Explanations
information related to legislative procedures, voting outcomes, and political events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
453
+0.09
0.3%
604
+0.08
0.2%
377
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1922
+0.09
0.02
377
+0.08
0.02
453
+0.08
0.02
Negative Logits
unwarran
-1.24
impractica
-1.21
disagre
-1.12
tolerably
-1.11
indestru
-1.11
liberality
-1.07
caprice
-1.06
unlaw
-1.00
reluct
-1.00
greate
-0.99
POSITIVE LOGITS
kafe
0.65
keramik
0.64
silikon
0.63
alho
0.62
komik
0.60
kooper
0.57
infrastruktur
0.57
alkoh
0.57
kosme
0.56
lanterna
0.56
Activations Density 0.057%