INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.6%
1741
+0.06
0.3%
1870
+0.05
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.50
disgra
-2.25
ineffec
-2.25
horrend
-2.22
reluct
-2.15
belliger
-2.10
shenan
-2.10
exasper
-2.08
unlaw
-2.08
ruinous
-2.05
POSITIVE LOGITS
<bos>
12.43
GEBURTSDATUM
2.59
expandindo
2.52
betweenstory
2.29
Autoritní
2.24
kasarigan
2.13
Италијани
2.11
LookAnd
2.10
Administrativna
2.09
تقاوى
2.09
Activations Density 0.000%
No Known Activations
This feature has no known activations.