INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.31
1.3%
1741
+0.05
0.2%
9
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.31
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
unspeak
-2.00
unlaw
-1.74
ineffec
-1.71
horrend
-1.70
ruinous
-1.70
laug
-1.67
belliger
-1.65
Daven
-1.62
unavoid
-1.58
reluct
-1.57
POSITIVE LOGITS
<bos>
10.85
expandindo
1.96
betweenstory
1.95
Autoritní
1.91
GEBURTSDATUM
1.90
kasarigan
1.74
Италијани
1.73
LookAnd
1.72
Panamoan
1.66
Italijani
1.63
Activations Density 0.000%
No Known Activations
This feature has no known activations.