INDEX
Explanations
phrases expressing a high degree or intensity of something
phrases indicating strong feelings or reactions
New Auto-Interp
Negative Logits
ugal
-0.64
Angola
-0.64
Seller
-0.63
yne
-0.62
Afgh
-0.61
hoops
-0.61
ammy
-0.60
Hermes
-0.59
Shiite
-0.58
aiden
-0.58
POSITIVE LOGITS
rox
0.72
smanship
0.71
itated
0.70
itates
0.69
itional
0.69
deserve
0.69
itous
0.68
unus
0.67
mone
0.66
borgh
0.65
Activations Density 0.189%