INDEX
Explanations
references to farm animals, particularly sheep
references to sheep and lambs
New Auto-Interp
Negative Logits
SPONSORED
-0.78
ENTS
-0.75
validity
-0.74
fortun
-0.72
GOODMAN
-0.68
vehement
-0.68
indo
-0.68
disadvant
-0.68
ATIONS
-0.65
nostalg
-0.65
POSITIVE LOGITS
dogs
1.20
dog
1.17
ishly
1.10
skin
1.03
poke
0.98
stra
0.88
girls
0.88
meat
0.86
bats
0.85
bones
0.84
Activations Density 0.018%