INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.25
0.8%
1974
+0.04
0.1%
1575
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.25
0.00
0
-0.04
0.00
1
-0.04
0.00
Negative Logits
reluct
-8.07
shenan
-7.80
increa
-7.67
impra
-7.57
depic
-7.52
encomp
-7.43
disagre
-7.43
maneu
-7.34
unspeak
-7.25
snoopy
-7.17
POSITIVE LOGITS
<bos>
9.56
Walkover
2.99
Paglinawan
2.63
Himo
2.54
betweenstory
2.49
Baillargeon
2.43
Italijani
2.43
PerformLayout
2.40
***!
2.40
GraphicsUnit
2.36
Activations Density 0.000%
No Known Activations
This feature has no known activations.