INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.4%
1741
+0.06
0.3%
440
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.94
unlaw
-1.77
reluct
-1.62
ruinous
-1.61
exasper
-1.61
belliger
-1.60
disgra
-1.60
ineffec
-1.56
Daven
-1.56
horrend
-1.53
POSITIVE LOGITS
<bos>
11.03
GEBURTSDATUM
1.99
expandindo
1.96
Administrativna
1.82
Personendaten
1.75
Autoritní
1.74
betweenstory
1.72
تقاوى
1.72
Italijani
1.68
تضيفلها
1.66
Activations Density 0.000%
No Known Activations
This feature has no known activations.