INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.35
1.5%
1741
+0.06
0.2%
325
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.35
0.00
0
-0.06
0.00
1
-0.04
0.00
Negative Logits
only
-0.96
even
-0.95
не
-0.95
after
-0.93
might
-0.92
when
-0.92
would
-0.92
yet
-0.91
но
-0.91
may
-0.91
POSITIVE LOGITS
<bos>
10.47
encomp
3.68
guarante
3.64
affor
3.61
fuf
3.60
?...
3.58
effe
3.57
increa
3.55
!...
3.52
squa
3.51
Activations Density 0.000%
No Known Activations
This feature has no known activations.