INDEX
Explanations
mentions of the word 'lion' and related terms
references to lions
New Auto-Interp
Negative Logits
mble
-0.85
chell
-0.76
ilk
-0.76
Ñı
-0.74
lying
-0.73
matter
-0.70
aeda
-0.69
ACTION
-0.67
ÑĮ
-0.67
skirts
-0.64
POSITIVE LOGITS
esses
1.28
fish
1.10
lions
1.09
ess
1.01
eye
0.98
ous
0.94
lion
0.94
osaurs
0.92
odon
0.91
toe
0.81
Activations Density 0.016%