INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.3%
76
+0.05
0.2%
1741
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.78
shenan
-1.54
FTFY
-1.50
Wtf
-1.50
despotism
-1.45
belliger
-1.44
ineffec
-1.42
reluct
-1.39
laug
-1.39
miscon
-1.38
POSITIVE LOGITS
<bos>
10.88
expandindo
1.97
autorytatywna
1.91
Autoritní
1.81
kasarigan
1.75
GEBURTSDATUM
1.75
betweenstory
1.74
LookAnd
1.66
kaarangay
1.61
Билгалдахарш
1.60
Activations Density 0.000%
No Known Activations
This feature has no known activations.