INDEX
Explanations
mentions of hunting or hunters
references to the concept of "hunter" and related terms
New Auto-Interp
Negative Logits
ription
-0.77
iating
-0.75
iment
-0.75
olor
-0.72
enza
-0.71
roach
-0.67
adiq
-0.67
ually
-0.66
onent
-0.66
isive
-0.66
POSITIVE LOGITS
hunter
1.10
sonian
0.96
gat
0.94
esses
0.92
hunters
0.86
hunter
0.82
ju
0.76
cki
0.76
gery
0.75
hunting
0.74
Activations Density 0.016%