INDEX
Explanations
words related to sheep
references to sheep
New Auto-Interp
Negative Logits
ENTS
-0.76
SPONSORED
-0.72
GOODMAN
-0.71
vehement
-0.70
nostalg
-0.66
arcity
-0.65
nce
-0.64
indo
-0.63
fict
-0.63
fracturing
-0.63
POSITIVE LOGITS
ishly
1.11
dog
1.11
dogs
1.10
skin
1.06
poke
0.96
girls
0.85
bones
0.85
meat
0.85
sheep
0.84
folk
0.83
Activations Density 0.004%