INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.26
0.8%
1871
+0.06
0.2%
1691
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.26
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
reluct
-6.06
shenan
-5.88
impra
-5.87
unspeak
-5.73
increa
-5.64
disagre
-5.63
depic
-5.57
snoopy
-5.41
encomp
-5.40
apprehen
-5.31
POSITIVE LOGITS
<bos>
8.10
Walkover
2.57
Paglinawan
2.42
Himo
2.30
himo
2.21
***!
2.21
betweenstory
2.13
'\\;'
2.12
nakalista
2.11
GEBURTSDATUM
2.08
Activations Density 0.000%
No Known Activations
This feature has no known activations.