INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.31
1.2%
906
+0.06
0.2%
482
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.31
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
неу
-0.76
bombings
-0.74
failed
-0.72
一样
-0.71
но
-0.71
失败
-0.71
Там
-0.70
atrocities
-0.70
无法
-0.70
程序
-0.70
POSITIVE LOGITS
<bos>
9.60
dispen
2.35
fuf
2.21
desir
2.13
embra
2.11
effe
2.11
?...
2.11
perfet
2.10
accla
2.09
acce
2.09
Activations Density 0.000%
No Known Activations
This feature has no known activations.