INDEX
Explanations
measurements related to food portions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
599
+0.32
1.2%
764
+0.25
0.9%
1842
+0.22
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
764
+0.32
0.09
856
+0.25
0.06
1842
+0.22
0.07
Negative Logits
<bos>
-0.84
GEBURTSDATUM
-0.77
bezeichneter
-0.68
ⓧ
-0.60
Савезне
-0.58
Fordítás
-0.58
Искәрмәләр
-0.58
SourceChecksum
-0.56
Personendaten
-0.55
ویکیپدی
-0.54
POSITIVE LOGITS
wien
0.99
erad
0.97
depic
0.95
maneu
0.94
vns
0.94
blos
0.92
snoopy
0.92
impra
0.92
berea
0.91
suscep
0.90
Activations Density 0.876%