INDEX
Explanations
technical and theoretical terms related to economics and philosophy
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1150
+0.17
0.5%
1343
+0.15
0.4%
872
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
924
+0.17
0.04
1150
+0.15
0.03
382
+0.11
0.03
Negative Logits
swarovski
-1.34
nutella
-1.27
ecru
-1.25
bordeaux
-1.24
„,
-1.23
murano
-1.21
traktor
-1.21
hairc
-1.21
fta
-1.20
myn
-1.20
POSITIVE LOGITS
p
0.74
pp
0.73
page
0.63
vol
0.59
Vol
0.57
§
0.57
стр
0.55
section
0.55
p
0.54
Volume
0.54
Activations Density 0.156%