INDEX
Explanations
specific references to a particular place or location
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.20
1.2%
1757
+0.10
0.6%
421
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
814
+0.20
0.05
1491
+0.10
0.04
421
+0.10
0.04
Negative Logits
<bos>
-3.46
contentLoaded
-0.60
modernize
-0.60
//---
-0.60
adjust
-0.59
rehabilitate
-0.58
<?
-0.58
/*++
-0.58
lift
-0.57
public
-0.55
POSITIVE LOGITS
maroc
1.25
ecru
1.22
ankara
1.20
bordeaux
1.18
seksi
1.09
swarovski
1.08
cartier
1.08
hairc
1.08
palio
1.07
milano
1.07
Activations Density 0.146%