INDEX
Explanations
statistics and opinions related to public sentiment and political views
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
381
+0.14
0.4%
2019
+0.13
0.4%
283
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
728
+0.14
0.03
1025
+0.13
0.03
1202
+0.11
0.02
Negative Logits
shenan
-1.77
unspeak
-1.77
snoopy
-1.73
gild
-1.68
gaily
-1.67
impra
-1.66
sophistic
-1.64
melange
-1.63
indescri
-1.62
parch
-1.61
POSITIVE LOGITS
alkoh
1.47
utop
1.45
kosme
1.44
silikon
1.41
kompati
1.39
republi
1.37
solidar
1.37
ortop
1.35
akut
1.35
meras
1.34
Activations Density 0.077%