INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.23
0.8%
2015
+0.05
0.2%
185
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.23
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
reluct
-4.34
shenan
-4.30
unspeak
-4.28
impra
-4.23
depic
-3.99
disagre
-3.97
increa
-3.91
apprehen
-3.90
disreg
-3.81
indestru
-3.79
POSITIVE LOGITS
<bos>
9.14
Walkover
2.33
Paglinawan
2.19
Himo
2.09
GEBURTSDATUM
2.07
Autoritní
2.04
'\\;'
1.99
betweenstory
1.98
expandindo
1.97
LookAnd
1.92
Activations Density 0.000%
No Known Activations
This feature has no known activations.