INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.20
0.6%
1912
+0.05
0.2%
1015
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.20
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
reluct
-8.34
shenan
-8.27
impra
-7.97
unspeak
-7.95
increa
-7.88
depic
-7.85
disagre
-7.83
encomp
-7.83
apprehen
-7.68
maneu
-7.50
POSITIVE LOGITS
<bos>
7.99
Walkover
3.39
Himo
2.96
Paglinawan
2.86
himo
2.76
***!
2.74
<",
2.68
Shetterly
2.66
expandindo
2.66
'\\;'
2.65
Activations Density 0.000%
No Known Activations
This feature has no known activations.