INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.24
0.7%
627
+0.04
0.1%
1150
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.24
0.00
0
-0.04
0.00
1
-0.04
0.00
Negative Logits
لينك
-0.70
tortura
-0.68
injus
-0.68
estancias
-0.67
SIGINT
-0.67
INVISIBLE
-0.66
Preguntas
-0.66
Throwable
-0.66
있
-0.65
համ
-0.65
POSITIVE LOGITS
<bos>
7.83
encomp
2.95
intersper
2.84
suscep
2.80
increa
2.76
maneu
2.75
guarante
2.72
accla
2.71
depic
2.71
affor
2.70
Activations Density 0.000%
No Known Activations
This feature has no known activations.