INDEX
Explanations
various elements related to visual media and citations
New Auto-Interp
Negative Logits
******************************************************************************↵
-0.16
Kirk
-0.15
ÛĮØ´ÙĨ
-0.15
bridal
-0.14
/embed
-0.14
prisoner
-0.14
129
-0.14
RL
-0.14
ochond
-0.14
/msg
-0.14
POSITIVE LOGITS
file
0.21
scre
0.19
EPA
0.18
ANI
0.18
Scre
0.18
picture
0.18
Picture
0.17
_twitter
0.16
File
0.16
0.15
Activations Density 0.020%