INDEX
Explanations
phrases describing physical objects or actions involving wrapping around something
instances of the word "around."
New Auto-Interp
Negative Logits
iPhone
-0.72
qua
-0.72
Tigers
-0.69
xual
-0.68
idy
-0.64
BT
-0.62
gotten
-0.60
inen
-0.60
Kardash
-0.59
phone
-0.58
POSITIVE LOGITS
abouts
0.95
corners
0.94
clock
0.78
unin
0.77
worms
0.72
ciating
0.70
worm
0.69
top
0.67
bys
0.66
world
0.66
Activations Density 0.049%