INDEX
Explanations
prepositions and phrases indicating relationships or connections in various contexts
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.04
3:0.13
4:0.03
5:0.05
6:0.07
7:0.34
8:0.05
9:0.05
10:0.07
11:0.06
Negative Logits
ype
-1.38
actionDate
-1.36
finger
-1.36
tymology
-1.33
fecture
-1.33
ugu
-1.31
ivid
-1.31
ppo
-1.29
umeric
-1.29
ashtra
-1.29
POSITIVE LOGITS
Cooldown
1.20
consecutive
1.20
Hawk
1.16
treadmill
1.15
Interstitial
1.14
throughput
1.13
miracles
1.10
Slayer
1.08
KC
1.07
BW
1.06
Activations Density 0.023%