INDEX
Explanations
terms related to vegetarianism and veganism
New Auto-Interp
Negative Logits
aad
-0.17
537
-0.17
elder
-0.15
urum
-0.15
atics
-0.14
æľ¯
-0.14
holder
-0.14
goog
-0.14
æľį
-0.14
illow
-0.14
POSITIVE LOGITS
gie
0.34
arian
0.28
arians
0.24
itarian
0.21
matter
0.20
atables
0.20
/fr
0.19
itable
0.18
atable
0.17
tables
0.17
Activations Density 0.009%