INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.19
0.6%
1803
+0.05
0.2%
230
+0.05
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.19
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
reluct
-3.84
unspeak
-3.81
impra
-3.79
disagre
-3.70
increa
-3.69
shenan
-3.58
apprehen
-3.52
encomp
-3.51
depic
-3.45
scrat
-3.44
POSITIVE LOGITS
<bos>
6.43
Autoritní
1.67
GEBURTSDATUM
1.65
Paglinawan
1.59
oredCriteria
1.58
***!
1.57
betweenstory
1.56
tagHelperRunner
1.53
PerformLayout
1.53
'\\;'
1.53
Activations Density 0.000%
No Known Activations
This feature has no known activations.