INDEX
Explanations
mentions of the name "Lisa."
New Auto-Interp
Negative Logits
chest
-0.18
leys
-0.16
.openg
-0.16
chnitt
-0.15
wind
-0.15
Pair
-0.15
ga
-0.15
коÑĢиÑģÑĤ
-0.15
imest
-0.15
YST
-0.15
POSITIVE LOGITS
Ludwig
0.17
Atlantic
0.17
ANE
0.15
ngle
0.15
apore
0.14
rap
0.14
onde
0.14
getti
0.14
allis
0.14
adena
0.14
Activations Density 0.008%