INDEX
Explanations
legislative bill references and political topics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.10
0.3%
453
+0.09
0.3%
507
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1597
+0.10
0.02
507
+0.09
0.03
366
+0.09
0.02
Negative Logits
reluct
-1.21
disagre
-1.13
disreg
-1.13
apprehen
-1.08
withal
-1.06
scrat
-1.04
ingrat
-1.02
indestru
-1.01
swarovski
-1.01
gaily
-0.99
POSITIVE LOGITS
keramik
1.08
optik
1.06
ekos
1.04
makro
0.96
kafe
0.96
teras
0.95
induk
0.95
alkoh
0.94
silikon
0.93
elek
0.92
Activations Density 0.113%