INDEX
Explanations
phrases related to politics, legislation, and government processes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.27
0.9%
1967
+0.18
0.6%
1385
+0.15
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
16
+0.27
0.12
1967
+0.18
0.09
50
+0.15
0.08
Negative Logits
shenan
-1.01
intersper
-1.00
eqn
-0.97
encomp
-0.94
yoda
-0.94
logarith
-0.93
inappro
-0.91
maneu
-0.90
scrat
-0.89
disreg
-0.89
POSITIVE LOGITS
asisten
0.70
ideolog
0.69
solidar
0.68
cemento
0.68
Siria
0.66
monaster
0.65
legislat
0.65
minuta
0.65
vecin
0.64
dici
0.64
Activations Density 0.708%