INDEX
Explanations
phrases related to media and storytelling, particularly in literature and film contexts
New Auto-Interp
Negative Logits
769
-0.16
bart
-0.15
amba
-0.15
oras
-0.14
agine
-0.14
ells
-0.14
InSection
-0.14
_mono
-0.14
Resp
-0.14
Mention
-0.14
POSITIVE LOGITS
rats
0.17
ado
0.15
cak
0.14
entar
0.14
avel
0.14
.Sdk
0.14
scar
0.14
ef
0.14
arring
0.14
ocab
0.14
Activations Density 0.138%