INDEX
Explanations
expressions indicating readiness or preparation for action
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.08
3:0.30
4:0.02
5:0.02
6:0.04
7:0.08
8:0.07
9:0.10
10:0.06
11:0.13
Negative Logits
Downloadha
-1.33
Haunted
-1.26
Watkins
-1.25
UA
-1.24
hemat
-1.22
ahan
-1.20
ARS
-1.20
Lerner
-1.18
jiang
-1.17
Nationals
-1.16
POSITIVE LOGITS
sacrific
1.75
disg
1.60
pu
1.47
ACTIONS
1.44
abl
1.38
unle
1.33
withd
1.32
cel
1.29
combust
1.25
conting
1.24
Activations Density 0.012%