INDEX
Explanations
information regarding email updates, news content, promotions, and special offers
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
678
+0.19
0.6%
1403
+0.16
0.5%
738
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
678
+0.19
0.05
1403
+0.16
0.02
76
+0.10
0.04
Negative Logits
réunions
-0.84
déclarations
-0.78
négociations
-0.77
prochaines
-0.74
leçons
-0.74
journées
-0.72
vœux
-0.71
économies
-0.67
séjours
-0.65
bénéfices
-0.65
POSITIVE LOGITS
izational
1.03
kram
1.00
alpes
0.99
lele
0.99
moza
0.97
peculi
0.94
kef
0.94
labd
0.93
logis
0.93
glan
0.93
Activations Density 0.275%