INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.29
1.0%
1253
+0.07
0.2%
1755
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.29
0.00
0
-0.07
0.00
1
-0.04
0.00
Negative Logits
unspeak
-1.89
horrend
-1.73
ineffec
-1.72
shenan
-1.61
belliger
-1.60
laug
-1.56
ruinous
-1.51
unbear
-1.50
exasper
-1.50
miscon
-1.48
POSITIVE LOGITS
<bos>
8.99
GEBURTSDATUM
1.98
expandindo
1.86
betweenstory
1.80
Geplaatst
1.77
Paglinawan
1.73
Autoritní
1.69
LookAnd
1.64
Personendaten
1.61
EndGlobalSection
1.61
Activations Density 0.000%
No Known Activations
This feature has no known activations.