INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.28
0.9%
200
+0.06
0.2%
2030
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.28
0.00
0
-0.06
0.00
1
-0.06
0.00
Negative Logits
reluct
-7.41
increa
-7.00
shenan
-6.97
impra
-6.95
disagre
-6.80
depic
-6.73
indestru
-6.71
maneu
-6.56
inev
-6.54
encomp
-6.53
POSITIVE LOGITS
<bos>
9.09
Walkover
2.63
Paglinawan
2.48
GEBURTSDATUM
2.43
betweenstory
2.34
RegressionTest
2.19
Panamoan
2.17
expandindo
2.13
kasarigan
2.09
SharedDtor
2.09
Activations Density 0.000%
No Known Activations
This feature has no known activations.