INDEX
Explanations
mentions of locations and organizations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
856
+0.14
0.4%
50
+0.13
0.4%
1842
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
856
+0.14
0.05
939
+0.13
0.06
849
+0.10
0.05
Negative Logits
'\\;'
-0.74
Paglinawan
-0.73
Билгалдахарш
-0.72
bootstrapcdn
-0.70
<bos>
-0.70
fml
-0.68
RTSC
-0.66
boutin
-0.64
ISPR
-0.63
ibrill
-0.63
POSITIVE LOGITS
reluct
2.07
accla
1.93
increa
1.93
inev
1.88
encomp
1.86
affor
1.85
shenan
1.82
unve
1.80
guarante
1.80
snoopy
1.79
Activations Density 0.267%