INDEX
Explanations
mentions of individuals or locations in news articles
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.20
0.6%
845
+0.12
0.4%
856
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.20
0.03
1343
+0.12
0.03
1585
+0.12
0.02
Negative Logits
<bos>
-0.59
kombi
-0.59
انيف
-0.54
disambiguazione
-0.54
bezeichneter
-0.51
Được
-0.49
Paglinawan
-0.47
GEBURTSDATUM
-0.47
тьяна
-0.46
Thiết
-0.44
POSITIVE LOGITS
lamella
0.81
elems
0.80
newArr
0.75
rowCount
0.74
dolom
0.71
noOf
0.70
gne
0.69
friable
0.69
unve
0.68
sherds
0.68
Activations Density 0.082%