INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.7%
1870
+0.07
0.4%
1253
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.07
0.00
1
-0.07
0.00
Negative Logits
unspeak
-2.25
belliger
-2.08
horrend
-2.05
ineffec
-1.97
ruinous
-1.96
miscon
-1.95
laug
-1.90
exasper
-1.88
unavoid
-1.85
shenan
-1.82
POSITIVE LOGITS
<bos>
12.39
expandindo
2.72
GEBURTSDATUM
2.61
betweenstory
2.44
Autoritní
2.33
'\\;'
2.23
Walkover
2.15
Paglinawan
2.09
LookAnd
2.06
autorytatywna
2.04
Activations Density 0.000%
No Known Activations
This feature has no known activations.