INDEX
Explanations
quotations or reported speech indicated by quotation marks
occurrences of quotations and punctuation marks indicating speech or dialogue
New Auto-Interp
Negative Logits
ouver
-0.81
ilyn
-0.80
oid
-0.79
inki
-0.77
atted
-0.77
ible
-0.75
AGES
-0.75
CLSID
-0.74
rikes
-0.74
oids
-0.72
POSITIVE LOGITS
Zoro
0.72
!--
0.68
cipled
0.68
mington
0.66
indec
0.64
ricanes
0.63
````
0.59
backer
0.58
Page
0.56
âĢ¢âĢ¢âĢ¢âĢ¢
0.56
Activations Density 0.030%