INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.36
1.9%
50
+0.05
0.3%
1870
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.36
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
Những
-1.01
INVISIBLE
-1.00
Aunque
-0.98
Sự
-0.97
GONE
-0.97
भी
-0.96
لينك
-0.95
Muchos
-0.95
ে
-0.94
EINVAL
-0.94
POSITIVE LOGITS
<bos>
11.62
encomp
4.25
fuf
4.22
affor
4.18
guarante
4.16
increa
4.12
squa
4.09
fta
4.05
effe
4.04
emphat
4.02
Activations Density 0.000%
No Known Activations
This feature has no known activations.