INDEX
Explanations
references to science fiction as a genre
New Auto-Interp
Negative Logits
attachment
-0.15
Attachment
-0.15
okie
-0.14
æ¸Ī
-0.14
sentiment
-0.14
ifar
-0.14
Attachment
-0.14
lew
-0.14
roke
-0.14
orsi
-0.14
POSITIVE LOGITS
æĥ
0.16
Dahl
0.16
vor
0.16
ÑħÑĥд
0.15
å®Ļ
0.15
纪
0.14
chor
0.14
omu
0.14
²
0.14
-transitional
0.14
Activations Density 0.124%