INDEX
Explanations
descriptive words related to beverages, particularly happy and refreshing ones
adjectives and descriptors related to enjoyment and happiness
New Auto-Interp
Negative Logits
rait
-0.77
inen
-0.74
yrim
-0.69
RIP
-0.69
uberty
-0.69
uther
-0.68
itans
-0.68
ilitation
-0.68
itu
-0.68
igration
-0.68
POSITIVE LOGITS
pants
0.99
ness
0.98
nesses
0.98
zzy
0.84
seas
0.84
sounding
0.76
Pry
0.76
ppy
0.76
gritty
0.74
funky
0.74
Activations Density 0.040%