INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.5%
1870
+0.05
0.2%
1535
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.38
horrend
-2.14
ineffec
-2.13
shenan
-2.05
reluct
-2.02
disgra
-2.01
unlaw
-1.95
impra
-1.95
impractica
-1.95
miscon
-1.92
POSITIVE LOGITS
<bos>
11.72
GEBURTSDATUM
2.42
expandindo
2.39
Autoritní
2.13
betweenstory
2.13
تقاوى
1.98
'\\;'
1.93
Administrativna
1.93
LookAnd
1.92
Walkover
1.88
Activations Density 0.000%
No Known Activations
This feature has no known activations.