INDEX
Explanations
elements of humor and comedy in various contexts
New Auto-Interp
Negative Logits
inous
-0.15
erah
-0.15
uries
-0.14
/**↵↵
-0.14
orgeous
-0.14
heyec
-0.13
.nih
-0.13
KANJI
-0.13
whispers
-0.13
ForObject
-0.13
POSITIVE LOGITS
humor
0.51
humour
0.48
comedy
0.44
humorous
0.43
laughs
0.42
laughter
0.40
jokes
0.39
satire
0.39
joke
0.39
laugh
0.38
Activations Density 1.214%