INDEX
Explanations
references to milk and dairy products
New Auto-Interp
Negative Logits
rat
-0.15
eer
-0.14
ius
-0.14
unei
-0.14
AGENT
-0.13
oxic
-0.13
ional
-0.13
ebek
-0.13
arat
-0.13
edi
-0.13
POSITIVE LOGITS
endale
0.17
erton
0.17
rippling
0.16
milk
0.16
ToProps
0.15
960
0.14
edriver
0.14
%f
0.14
Mig
0.14
amm
0.14
Activations Density 0.019%