INDEX
Explanations
beauty-related terms and product names
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.22
0.8%
876
+0.09
0.4%
736
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.22
0.07
1366
+0.09
0.05
1801
+0.08
0.05
Negative Logits
<bos>
-2.96
ⓧ
-0.99
/***
-0.87
Autoritní
-0.80
///**
-0.76
Kontrola
-0.72
<?
-0.72
PerformLayout
-0.70
lutar
-0.70
<tfoot>
-0.68
POSITIVE LOGITS
affor
1.25
maroc
1.23
malheure
1.19
stockholm
1.15
meis
1.14
increa
1.13
maneu
1.11
impra
1.09
balkon
1.06
lidl
1.05
Activations Density 0.542%