INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.25
0.8%
507
+0.04
0.1%
995
+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
-7.97
shenan
-7.75
increa
-7.57
impra
-7.57
depic
-7.47
disagre
-7.39
encomp
-7.34
unspeak
-7.33
maneu
-7.18
apprehen
-7.09
POSITIVE LOGITS
<bos>
9.81
Walkover
3.21
Himo
2.93
Paglinawan
2.89
GEBURTSDATUM
2.69
himo
2.69
Autoritní
2.65
'\\;'
2.58
Italijani
2.57
betweenstory
2.57
Activations Density 0.000%
No Known Activations
This feature has no known activations.