INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.14
0.4%
845
+0.05
0.1%
1089
+0.05
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.14
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
reluct
-8.83
increa
-8.77
impra
-8.63
depic
-8.43
shenan
-8.42
disagre
-8.41
encomp
-8.38
affor
-8.24
maneu
-8.20
snoopy
-8.03
POSITIVE LOGITS
<bos>
5.04
Walkover
2.56
himo
2.36
***!
2.34
Himo
2.31
Shetterly
2.26
│
2.23
<",
2.17
Baillargeon
2.16
Paglinawan
2.14
Activations Density 0.000%
No Known Activations
This feature has no known activations.