INDEX
Explanations
mentions of specific individuals and their roles in significant events
New Auto-Interp
Negative Logits
à¸ļาล
-0.16
conc
-0.14
mpar
-0.14
VersionUID
-0.14
vertime
-0.13
Conc
-0.13
uter
-0.13
ÙĤص
-0.13
lace
-0.13
Callbacks
-0.13
POSITIVE LOGITS
scene
0.18
detail
0.18
view
0.17
sign
0.17
Detail
0.17
Scene
0.16
detail
0.16
Detail
0.16
views
0.15
sunset
0.15
Activations Density 0.175%