INDEX
Explanations
terms related to rhetorical strategies and speech patterns
New Auto-Interp
Negative Logits
oming
-0.16
chner
-0.15
aries
-0.15
ello
-0.15
Parcel
-0.15
chestra
-0.15
inis
-0.15
brit
-0.14
ÑĤож
-0.14
arily
-0.14
POSITIVE LOGITS
incinn
0.15
tog
0.15
aticon
0.15
angi
0.14
ingt
0.14
osit
0.14
rang
0.14
aylight
0.14
ATUS
0.14
osis
0.14
Activations Density 0.004%