INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.5%
1741
+0.07
0.3%
1870
+0.06
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.07
0.00
1
-0.06
0.00
Negative Logits
unspeak
-2.03
disgra
-1.90
ineffec
-1.86
unlaw
-1.86
belliger
-1.86
ruinous
-1.82
horrend
-1.78
impractica
-1.74
laug
-1.69
exasper
-1.69
POSITIVE LOGITS
<bos>
11.81
expandindo
2.41
GEBURTSDATUM
2.38
betweenstory
2.16
kasarigan
2.11
Autoritní
2.06
Италијани
1.98
تقاوى
1.98
Paglinawan
1.94
Italijani
1.89
Activations Density 0.000%
No Known Activations
This feature has no known activations.