INDEX
Explanations
strings related to software and data management
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
382
+0.09
0.3%
2034
+0.09
0.3%
184
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.09
0.06
736
+0.09
0.05
1265
+0.09
0.04
Negative Logits
trovar
-0.70
jugos
-0.68
saper
-0.61
dè
-0.61
asfal
-0.60
scopri
-0.59
anzi
-0.58
soggior
-0.58
veneta
-0.58
pregi
-0.57
POSITIVE LOGITS
whereas
1.24
whereas
1.22
tandis
0.99
Whereas
0.92
while
0.81
Whereas
0.80
Meanwhile
0.79
meanwhile
0.78
sedangkan
0.74
conversely
0.73
Activations Density 0.420%