INDEX
Explanations
references to prey and predatory relationships in the text
New Auto-Interp
Negative Logits
olie
-0.15
oi
-0.15
ksen
-0.14
limburg
-0.14
538
-0.14
_REFER
-0.14
Gerr
-0.14
massaggi
-0.13
breadcrumbs
-0.13
urga
-0.13
POSITIVE LOGITS
lore
0.17
isher
0.15
eden
0.15
apt
0.15
SPA
0.14
ohen
0.14
ikt
0.14
輪
0.14
olson
0.14
edBy
0.14
Activations Density 0.008%