INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.6%
1870
+0.08
0.4%
1120
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.08
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.80
horrend
-2.50
ineffec
-2.45
shenan
-2.37
miscon
-2.36
laug
-2.35
reluct
-2.34
impra
-2.31
unavoid
-2.27
disgra
-2.24
POSITIVE LOGITS
<bos>
12.27
expandindo
2.66
GEBURTSDATUM
2.63
betweenstory
2.35
Autoritní
2.35
kasarigan
2.19
Walkover
2.15
تقاوى
2.14
Administrativna
2.12
Paglinawan
2.12
Activations Density 0.000%
No Known Activations
This feature has no known activations.