INDEX
Explanations
financial or budget-related information
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2034
+0.08
0.2%
1253
+0.08
0.2%
859
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.08
0.04
1818
+0.08
0.04
736
+0.07
0.04
Negative Logits
smtplib
-0.64
serre
-0.60
vernis
-0.59
miniatura
-0.58
cannes
-0.57
tabac
-0.57
Secrétaire
-0.56
oliveira
-0.56
pié
-0.56
bezeichneter
-0.56
POSITIVE LOGITS
reluct
0.65
downvotes
0.64
amounting
0.63
attemp
0.62
maneu
0.61
arou
0.61
downvoted
0.58
apprehen
0.57
(>
0.57
upvoted
0.56
Activations Density 0.303%