INDEX
Explanations
file-related attributes and metadata
New Auto-Interp
Negative Logits
onta
-0.14
oze
-0.14
į°ìĿ´
-0.13
edin
-0.13
)+↵
-0.13
оÑĤв
-0.13
Binder
-0.13
norm
-0.13
.RightToLeft
-0.13
equival
-0.13
POSITIVE LOGITS
lic
0.17
ingo
0.16
ogens
0.16
haus
0.15
VOKE
0.15
iffies
0.15
ached
0.15
elsey
0.14
ache
0.14
esh
0.14
Activations Density 0.002%