INDEX
Explanations
keywords related to sales promotions and deals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1052
+0.19
1.1%
341
+0.16
0.9%
31
+0.15
0.9%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1052
+0.19
0.04
31
+0.16
0.04
478
+0.15
0.02
Negative Logits
vestito
-0.69
<bos>
-0.67
hyrchwyd
-0.66
Alford
-0.63
Cá
-0.59
Celui
-0.58
Sébastien
-0.57
Dunbar
-0.56
Quoi
-0.56
Bartol
-0.55
POSITIVE LOGITS
Bund
0.89
bundles
0.83
Bundle
0.78
bundle
0.78
bund
0.77
bund
0.74
Bundles
0.71
bundled
0.71
Bundle
0.71
Bund
0.70
Activations Density 0.592%