INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.07
1:0.09
2:0.08
3:0.09
4:0.09
5:0.08
6:0.07
7:0.08
8:0.07
9:0.07
10:0.09
11:0.08
Negative Logits
mute
-1.56
Detective
-1.55
detective
-1.53
perjury
-1.53
slurs
-1.50
];
-1.47
fax
-1.42
understatement
-1.42
erie
-1.41
RECT
-1.40
POSITIVE LOGITS
inav
1.75
asca
1.66
jong
1.63
itiz
1.58
kefeller
1.48
oplan
1.47
sov
1.46
htaking
1.44
ionic
1.43
continental
1.42
Activations Density 0.000%
No Known Activations
This feature has no known activations.