INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.07
1:0.08
2:0.08
3:0.08
4:0.08
5:0.10
6:0.08
7:0.06
8:0.08
9:0.09
10:0.07
11:0.08
Negative Logits
acebook
-1.98
ciating
-1.93
�
-1.73
affili
-1.73
orse
-1.72
reditary
-1.68
ailability
-1.67
atures
-1.67
vant
-1.67
staking
-1.66
POSITIVE LOGITS
shoot
1.82
Beat
1.68
programme
1.52
wear
1.51
reath
1.48
OLED
1.46
rocket
1.44
owl
1.43
masterpiece
1.43
Ky
1.41
Activations Density 0.000%
No Known Activations
This feature has no known activations.