INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.22
0.7%
47
+0.05
0.2%
1712
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.22
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
reluct
-8.43
increa
-8.31
shenan
-8.13
impra
-8.03
depic
-7.96
encomp
-7.91
maneu
-7.90
affor
-7.81
disagre
-7.80
snoopy
-7.62
POSITIVE LOGITS
<bos>
8.15
Walkover
3.12
Paglinawan
2.59
Himo
2.56
'\\;'
2.43
***!
2.38
Baillargeon
2.36
Réponses
2.36
للاسماء
2.36
Shetterly
2.35
Activations Density 0.000%
No Known Activations
This feature has no known activations.