INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.19
0.6%
344
+0.06
0.2%
482
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.19
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
shenan
-6.65
reluct
-6.61
unspeak
-6.42
impra
-6.32
increa
-6.26
disagre
-6.24
encomp
-6.17
depic
-6.12
maneu
-6.04
apprehen
-6.04
POSITIVE LOGITS
<bos>
7.45
Paglinawan
2.65
Himo
2.61
Walkover
2.56
***!
2.35
Baillargeon
2.25
himo
2.25
Autoritní
2.19
Shetterly
2.18
'\\;'
2.17
Activations Density 0.000%
No Known Activations
This feature has no known activations.