INDEX
Explanations
phrases related to the United Nations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
314
+0.11
0.4%
58
+0.11
0.4%
1994
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1994
+0.11
0.02
1425
+0.11
0.03
86
+0.10
0.02
Negative Logits
intersper
-0.96
solicited
-0.83
sightly
-0.81
impra
-0.76
overcrow
-0.76
scrat
-0.74
intermitt
-0.74
disreg
-0.72
resurre
-0.72
compromising
-0.69
POSITIVE LOGITS
UN
0.95
UN
0.91
Nations
0.67
Unidas
0.60
ONU
0.58
Un
0.57
Unies
0.55
fono
0.54
Un
0.54
protokol
0.54
Activations Density 0.088%