INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.6%
1870
+0.07
0.4%
1741
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.07
0.00
1
-0.07
0.00
Negative Logits
unspeak
-2.12
disgra
-1.86
unlaw
-1.85
belliger
-1.84
ineffec
-1.83
ruinous
-1.79
horrend
-1.78
laug
-1.73
Daven
-1.73
exasper
-1.73
POSITIVE LOGITS
<bos>
12.37
expandindo
2.46
GEBURTSDATUM
2.30
Autoritní
2.20
betweenstory
2.19
kasarigan
2.16
تقاوى
1.99
Италијани
1.97
Administrativna
1.97
Geplaatst
1.96
Activations Density 0.000%
No Known Activations
This feature has no known activations.