INDEX
Explanations
words related to sarcasm or mocking tones
present participles and adjectives with a playful or humorous tone
New Auto-Interp
Negative Logits
ĻĤ
-0.79
OTOS
-0.76
URA
-0.69
cryst
-0.69
ãĥķãĤ©
-0.68
srf
-0.68
MSN
-0.68
AAF
-0.67
ãĥ´
-0.66
ãĥ¯ãĥ³
-0.66
POSITIVE LOGITS
ingly
1.06
bery
0.99
inducing
0.99
iness
0.95
y
0.91
fest
0.90
puff
0.90
ily
0.89
ings
0.87
iest
0.86
Activations Density 0.270%