INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.07
1:0.08
2:0.08
3:0.09
4:0.08
5:0.07
6:0.08
7:0.08
8:0.07
9:0.07
10:0.07
11:0.09
Negative Logits
eq
-1.71
erent
-1.70
stood
-1.62
oward
-1.61
contrary
-1.61
ii
-1.56
ounded
-1.54
Progressive
-1.50
Mp
-1.49
ighed
-1.47
POSITIVE LOGITS
Frenzy
1.72
Hebdo
1.71
SAL
1.69
DragonMagazine
1.65
WARN
1.65
earance
1.64
rosis
1.61
dump
1.60
spraying
1.58
arenthood
1.56
Activations Density 0.000%
No Known Activations
This feature has no known activations.