INDEX
Explanations
instances of humor or comedic elements
references to humor and comedic elements
New Auto-Interp
Negative Logits
minster
-0.69
eding
-0.66
ameron
-0.64
uchs
-0.63
ECD
-0.63
emies
-0.62
FT
-0.60
yer
-0.60
Countries
-0.60
irements
-0.59
POSITIVE LOGITS
humor
1.19
humour
1.12
ously
0.90
satir
0.86
isma
0.84
laughter
0.81
banter
0.81
weed
0.79
comedic
0.79
humorous
0.76
Activations Density 0.007%