INDEX
Explanations
references to drinks, particularly cocktails and their ingredients
New Auto-Interp
Negative Logits
tm
-0.17
Realm
-0.15
ling
-0.15
áh
-0.14
lat
-0.14
_nl
-0.14
commerce
-0.13
èĮ¨
-0.13
Viv
-0.13
ober
-0.13
POSITIVE LOGITS
Mem
0.17
mem
0.17
105
0.16
arden
0.15
çŀ
0.14
quil
0.14
або
0.14
preserved
0.14
_mem
0.14
_MEM
0.14
Activations Density 0.291%