INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.08
1:0.05
2:0.09
3:0.08
4:0.08
5:0.08
6:0.07
7:0.09
8:0.09
9:0.09
10:0.08
11:0.07
Negative Logits
cited
-1.78
deputy
-1.72
interviewed
-1.71
Deputy
-1.70
deleted
-1.66
aired
-1.64
Sgt
-1.63
summ
-1.61
framed
-1.59
interim
-1.59
POSITIVE LOGITS
龍喚士
2.17
rious
2.15
enfranch
2.12
ophe
2.00
phia
1.98
irtual
1.97
peror
1.96
ASY
1.94
igious
1.94
ウス
1.94
Activations Density 0.000%
No Known Activations
This feature has no known activations.