INDEX
Explanations
phrases related to political advocacy and public opinion, particularly around the topics of abortion and minority rights
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
604
+0.09
0.3%
74
+0.08
0.2%
1253
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
81
+0.09
0.04
74
+0.08
0.04
119
+0.07
0.04
Negative Logits
pamph
-0.92
shenan
-0.70
disagre
-0.68
despotism
-0.67
endeavouring
-0.66
encomp
-0.65
unspeak
-0.64
apprehen
-0.64
attainments
-0.63
depic
-0.62
POSITIVE LOGITS
secco
0.79
fides
0.77
marrone
0.71
ideolog
0.70
voters
0.70
Jerusal
0.70
palio
0.70
potes
0.69
ristor
0.68
mercen
0.66
Activations Density 0.587%