INDEX
Explanations
source code related to creating, accessing, and managing orders through an API
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.20
0.6%
453
+0.14
0.4%
1871
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
876
+0.20
0.00
975
+0.14
0.01
753
+0.10
0.01
Negative Logits
lo
-0.68
again
-0.67
о
-0.67
and
-0.65
between
-0.65
themselves
-0.65
российской
-0.65
gobernador
-0.64
욱
-0.64
будин
-0.64
POSITIVE LOGITS
peppa
2.14
!...
2.03
?...
2.01
wien
1.95
coq
1.92
bordeaux
1.86
haup
1.84
espé
1.83
fluo
1.82
uniqu
1.82
Activations Density 0.048%