INDEX
Explanations
locations, organizations, and government-related information
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1387
+0.15
0.7%
1306
+0.14
0.7%
120
+0.12
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1387
+0.15
0.04
227
+0.14
0.05
1798
+0.12
0.04
Negative Logits
<bos>
-1.42
/**
-0.66
disbur
-0.65
overtook
-0.63
-0.63
circulate
-0.62
intersper
-0.61
stroked
-0.60
rejoined
-0.59
mustered
-0.59
POSITIVE LOGITS
Utah
1.27
Utah
1.22
morm
1.04
incess
0.96
Salt
0.94
alban
0.94
chèvre
0.91
alpes
0.90
Compagn
0.89
utah
0.87
Activations Density 0.434%