INDEX
Explanations
verbs related to actions taken by individuals in various contexts
New Auto-Interp
Head Attr Weights
0:0.06
1:0.03
2:0.17
3:0.12
4:0.03
5:0.14
6:0.05
7:0.05
8:0.06
9:0.11
10:0.09
11:0.03
Negative Logits
ADVERTISEMENT
-1.12
Bang
-1.09
Enlarge
-1.07
vibe
-1.06
Loading
-1.06
cerning
-1.05
versive
-1.04
fireworks
-1.02
Flag
-1.02
bie
-0.98
POSITIVE LOGITS
sugg
1.19
ンジ
1.08
himself
1.08
nonetheless
1.06
enegger
1.06
anson
1.05
herself
1.00
staking
0.98
rals
0.97
ュ
0.97
Activations Density 0.245%