INDEX
Explanations
specific animals such as sheep and goats, and related terms like wool and lamb
references to sheep and related agricultural terms
New Auto-Interp
Negative Logits
fortun
-0.78
validity
-0.76
ENTS
-0.76
unlaw
-0.72
indo
-0.72
horizont
-0.71
contrace
-0.70
disadvant
-0.70
SPONSORED
-0.69
ATION
-0.68
POSITIVE LOGITS
dogs
1.13
ishly
1.08
dog
1.06
skin
1.04
poke
0.95
stra
0.89
folk
0.86
wr
0.85
kies
0.83
girls
0.82
Activations Density 0.019%