INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.27
0.9%
814
+0.04
0.1%
609
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.27
0.00
0
-0.04
0.00
1
-0.04
0.00
Negative Logits
reluct
-7.78
shenan
-7.48
impra
-7.44
increa
-7.35
depic
-7.25
disagre
-7.17
encomp
-7.11
unspeak
-7.10
maneu
-6.92
affor
-6.85
POSITIVE LOGITS
<bos>
10.63
Walkover
3.20
Paglinawan
2.99
GEBURTSDATUM
2.82
expandindo
2.75
Himo
2.69
himo
2.67
Autoritní
2.66
-------------</
2.64
'\\;'
2.64
Activations Density 0.000%
No Known Activations
This feature has no known activations.