INDEX
Explanations
the proper noun "Yates"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
871
+0.13
0.5%
58
+0.13
0.5%
1994
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
58
+0.13
0.02
1406
+0.13
0.03
492
+0.12
0.03
Negative Logits
<bos>
-0.79
Será
-0.64
Nadie
-0.63
település
-0.62
alnız
-0.61
Примеча
-0.61
Alguna
-0.60
podr
-0.58
Selama
-0.58
Сол
-0.58
POSITIVE LOGITS
gmbh
1.10
bayern
1.02
grati
0.99
ananas
0.96
magis
0.96
alkoh
0.95
Y
0.94
cyr
0.93
pessi
0.93
baum
0.92
Activations Density 0.061%