INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.23
0.7%
720
+0.05
0.1%
76
+0.05
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.23
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
reluct
-9.23
increa
-8.90
impra
-8.87
shenan
-8.81
depic
-8.77
disagre
-8.54
maneu
-8.52
encomp
-8.49
affor
-8.37
strick
-8.25
POSITIVE LOGITS
<bos>
8.08
Walkover
3.22
Paglinawan
2.87
Himo
2.68
himo
2.59
'\\;'
2.57
***!
2.56
nakalista
2.52
HideFlags
2.47
Réponses
2.45
Activations Density 0.000%
No Known Activations
This feature has no known activations.