INDEX
Explanations
historical and geographical information
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
478
+0.15
0.5%
1967
+0.13
0.4%
1699
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1533
+0.15
0.03
478
+0.13
0.05
174
+0.12
0.04
Negative Logits
heapq
-0.75
Jakie
-0.74
Vrij
-0.73
Ostat
-0.68
Przyp
-0.67
Dlaczego
-0.65
Podob
-0.65
Deine
-0.65
Nichts
-0.64
Czym
-0.62
POSITIVE LOGITS
alkoh
1.68
silikon
1.57
kön
1.47
keramik
1.44
utop
1.41
sopr
1.40
mikrofon
1.40
kollek
1.38
pól
1.38
makro
1.36
Activations Density 0.095%