INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.38
2.5%
1741
+0.05
0.3%
1870
+0.04
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.38
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
unspeak
-1.78
belliger
-1.70
ruinous
-1.64
miscon
-1.60
ineffec
-1.59
horrend
-1.59
unlaw
-1.57
disgra
-1.55
laug
-1.55
odious
-1.48
POSITIVE LOGITS
<bos>
13.13
GEBURTSDATUM
2.63
expandindo
2.60
betweenstory
2.36
Autoritní
2.35
'\\;'
2.23
تقاوى
2.14
kasarigan
2.14
Administrativna
2.09
LookAnd
2.09
Activations Density 0.000%
No Known Activations
This feature has no known activations.