INDEX
Explanations
mentions of specific product names or brands, particularly food or drink items
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.12
0.4%
324
+0.11
0.3%
1173
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
324
+0.12
0.03
1819
+0.11
0.05
783
+0.09
0.03
Negative Logits
peppa
-0.69
nutella
-0.68
مرئيه
-0.64
bonbons
-0.64
quidem
-0.63
oreo
-0.62
Zucchini
-0.61
parma
-0.59
vito
-0.58
pinto
-0.57
POSITIVE LOGITS
krab
0.56
carrefour
0.55
SqlDataReader
0.52
bourg
0.50
chapelle
0.49
rocher
0.49
patrie
0.49
Président
0.48
Seni
0.48
sœur
0.46
Activations Density 0.317%