INDEX
Explanations
references to individuals in a casual or informal context, particularly "guy" and "gals."
New Auto-Interp
Negative Logits
swick
-0.18
cü
-0.16
iams
-0.15
ment
-0.15
áÅĻ
-0.14
ãģŁãģĹ
-0.14
ảy
-0.14
piring
-0.14
/bind
-0.14
shire
-0.14
POSITIVE LOGITS
/g
0.32
liner
0.21
who
0.19
-next
0.18
/G
0.17
who
0.17
z
0.17
iac
0.17
hattan
0.17
/team
0.17
Activations Density 0.039%