INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.21
0.7%
934
+0.06
0.2%
200
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.21
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
reluct
-7.07
increa
-6.88
impra
-6.83
shenan
-6.75
depic
-6.74
encomp
-6.63
disagre
-6.63
affor
-6.47
maneu
-6.36
unspeak
-6.36
POSITIVE LOGITS
<bos>
7.53
Walkover
2.42
Paglinawan
2.31
***!
2.14
'\\;'
2.11
betweenstory
2.06
Exacts
2.05
Baillargeon
2.04
Himo
2.03
<",
2.01
Activations Density 0.000%
No Known Activations
This feature has no known activations.