INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.21
0.6%
51
+0.06
0.2%
105
+0.04
0.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.21
0.00
0
-0.06
0.00
1
-0.04
0.00
Negative Logits
shenan
-5.87
reluct
-5.78
impra
-5.64
depic
-5.48
increa
-5.45
unspeak
-5.43
encomp
-5.41
maneu
-5.38
disagre
-5.33
affor
-5.17
POSITIVE LOGITS
<bos>
7.43
Walkover
2.48
Himo
2.40
Paglinawan
2.36
GEBURTSDATUM
2.29
himo
2.24
RegressionTest
2.18
Autoritní
2.12
ContentAsync
2.12
脚注の使い方
2.11
Activations Density 0.000%
No Known Activations
This feature has no known activations.