INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.08
3:0.10
4:0.07
5:0.07
6:0.08
7:0.07
8:0.07
9:0.09
10:0.08
11:0.08
Negative Logits
Naomi
-1.73
Peggy
-1.64
Watching
-1.63
washer
-1.61
Ivanka
-1.60
Deborah
-1.56
Macron
-1.55
Remem
-1.55
Omega
-1.54
Calories
-1.54
POSITIVE LOGITS
plet
1.95
Args
1.62
bast
1.62
itas
1.59
emetery
1.57
peat
1.57
ipel
1.57
RANT
1.57
IRD
1.55
itan
1.53
Activations Density 0.000%
No Known Activations
This feature has no known activations.