INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.27
0.9%
1798
+0.05
0.2%
583
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.27
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
reluct
-7.71
increa
-7.70
impra
-7.50
disagre
-7.26
shenan
-7.22
depic
-7.21
encomp
-7.14
affor
-7.11
inev
-7.03
maneu
-7.02
POSITIVE LOGITS
<bos>
9.60
Paglinawan
2.75
Walkover
2.70
GEBURTSDATUM
2.48
OGND
2.43
Himo
2.42
AddTagHelper
2.38
***!
2.36
betweenstory
2.33
GraphicsUnit
2.28
Activations Density 0.000%
No Known Activations
This feature has no known activations.