INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.37
2.4%
1870
+0.07
0.5%
1741
+0.06
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.37
0.00
0
-0.07
0.00
1
-0.06
0.00
Negative Logits
unspeak
-2.01
belliger
-1.90
ruinous
-1.80
ineffec
-1.78
unlaw
-1.78
horrend
-1.78
miscon
-1.76
impractica
-1.74
exasper
-1.71
laug
-1.69
POSITIVE LOGITS
<bos>
13.22
GEBURTSDATUM
2.54
expandindo
2.45
betweenstory
2.32
Autoritní
2.21
تقاوى
2.07
'\\;'
2.05
Administrativna
2.03
kasarigan
2.02
Italijani
1.95
Activations Density 0.000%
No Known Activations
This feature has no known activations.