INDEX
Explanations
words related to humor, satire, and parody
references to satire and parody
New Auto-Interp
Negative Logits
mom
-0.74
angu
-0.74
20439
-0.74
uls
-0.73
uchi
-0.71
--+
-0.70
amic
-0.68
Ability
-0.68
transfers
-0.67
amura
-0.67
POSITIVE LOGITS
satire
3.29
parody
3.10
satir
2.76
spoof
2.48
satirical
2.46
mockery
2.09
caricature
1.78
ridicule
1.57
blasphemy
1.50
imitation
1.46
Activations Density 0.044%