INDEX
Explanations
phrases related to systems, infrastructure, politics, and civilization
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.20
0.7%
1416
+0.12
0.4%
1265
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1416
+0.20
0.05
1183
+0.12
0.04
1398
+0.11
0.03
Negative Logits
Sklici
-0.66
তথ্যসূত্র
-0.56
Causas
-0.56
político
-0.55
Przyp
-0.52
İstinadlar
-0.51
iconst
-0.50
Glej
-0.50
Dziękuję
-0.50
Kesimpulan
-0.50
POSITIVE LOGITS
territo
0.72
traktor
0.68
brille
0.67
uhr
0.65
sena
0.65
saar
0.65
konkre
0.64
kark
0.64
klip
0.63
Mère
0.63
Activations Density 0.098%