INDEX
Explanations
terms related to food and beverage culture
New Auto-Interp
Negative Logits
wner
-0.17
JC
-0.15
antee
-0.15
ergus
-0.14
JP
-0.14
809
-0.14
MT
-0.14
Gian
-0.14
tw
-0.14
inel
-0.14
POSITIVE LOGITS
ascar
0.14
zeichnet
0.14
uhn
0.14
bsub
0.14
994
0.14
nam
0.14
Vil
0.14
ounder
0.14
ctxt
0.14
edi
0.14
Activations Density 0.048%