INDEX
Explanations
information related to restaurant details and descriptions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.32
1.3%
394
+0.12
0.5%
1971
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
394
+0.32
0.12
1937
+0.12
0.08
409
+0.08
0.08
Negative Logits
<bos>
-3.17
prepare
-0.66
arrange
-0.64
restore
-0.63
SourceChecksum
-0.61
<?
-0.59
displayquote
-0.58
activate
-0.57
let
-0.57
/**
-0.57
POSITIVE LOGITS
affor
1.52
swarovski
1.52
ecru
1.50
tupperware
1.46
impra
1.44
hairc
1.43
peppa
1.42
napoli
1.41
véhic
1.41
milano
1.41
Activations Density 2.078%