INDEX
Explanations
references to health-conscious beverage options
New Auto-Interp
Negative Logits
.nd
-0.06
.gov
-0.06
gente
-0.06
stu
-0.06
jealous
-0.06
rol
-0.06
aravel
-0.05
icari
-0.05
Fault
-0.05
fault
-0.05
POSITIVE LOGITS
ski
0.07
sal
0.07
ataka
0.07
oplast
0.07
illes
0.07
šet
0.07
macro
0.06
_TestCase
0.06
kok
0.06
cke
0.06
Activations Density 0.016%