INDEX
Explanations
HTML-like tags or angle brackets
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
103
+0.12
0.7%
289
+0.12
0.7%
478
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
103
+0.12
0.06
289
+0.12
0.07
124
+0.12
0.06
Negative Logits
aging
-1.60
](
-1.52
zos
-1.50
ager
-1.48
ORDER
-1.48
icos
-1.44
ressed
-1.42
ying
-1.39
process
-1.38
process
-1.38
POSITIVE LOGITS
forgiven
1.39
cases
1.38
pen
1.36
required
1.36
passages
1.32
âĤ¬âĦ¢
1.31
nights
1.31
kidding
1.30
inks
1.28
another
1.26
Activations Density 2.076%