INDEX
Explanations
mentions of the name "Frank."
New Auto-Interp
Negative Logits
ogy
-0.16
.au
-0.15
ahun
-0.14
ugas
-0.14
fat
-0.13
rganization
-0.13
ÏĦÏĮ
-0.13
aukee
-0.13
gv
-0.13
ibri
-0.13
POSITIVE LOGITS
enstein
0.18
bh
0.17
.TestCase
0.15
Ãľst
0.15
EDITOR
0.15
.synthetic
0.14
tails
0.14
.Pattern
0.14
TAIL
0.14
eted
0.14
Activations Density 0.004%