INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.35
1.5%
1870
+0.07
0.3%
1741
+0.06
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.35
0.00
0
-0.07
0.00
1
-0.06
0.00
Negative Logits
unspeak
-1.57
belliger
-1.57
unlaw
-1.53
ruinous
-1.48
miscon
-1.45
odious
-1.43
despotism
-1.39
horrend
-1.37
disgra
-1.35
impractica
-1.35
POSITIVE LOGITS
<bos>
11.48
GEBURTSDATUM
2.40
expandindo
2.25
Autoritní
1.96
LookAnd
1.88
تقاوى
1.88
betweenstory
1.85
Administrativna
1.84
kasarigan
1.83
Jeografia
1.81
Activations Density 0.000%
No Known Activations
This feature has no known activations.