INDEX
Explanations
instances of functions and function-related operations and syntax
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.16
0.5%
1150
+0.09
0.3%
1699
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
876
+0.16
0.00
2010
+0.09
0.02
1125
+0.08
0.02
Negative Logits
konserv
-0.67
Fonto
-0.64
alkoh
-0.64
kosme
-0.63
Öster
-0.62
akut
-0.62
Biografi
-0.61
radikal
-0.60
Referencoj
-0.60
Economía
-0.59
POSITIVE LOGITS
tupperware
1.21
peppa
1.17
affor
1.14
hairc
1.12
scrat
1.08
impra
1.06
strick
1.02
guarante
1.01
snoopy
1.00
tiffany
0.99
Activations Density 0.120%