INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.5%
108
+0.05
0.2%
1741
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
,
-1.48
-1.41
1
-1.36
.
-1.36
2
-1.34
3
-1.33
0
-1.32
8
-1.32
4
-1.31
5
-1.31
POSITIVE LOGITS
<bos>
11.14
GEBURTSDATUM
2.39
parteci
2.30
ⓧ
2.23
expandindo
2.21
sappi
2.17
dovr
2.13
betweenstory
2.10
Ottobre
2.09
Autoritní
2.03
Activations Density 0.000%
No Known Activations
This feature has no known activations.