INDEX
Explanations
instances of intense emotional or physical transformation
New Auto-Interp
Negative Logits
Aw
-0.17
Wilde
-0.15
flushed
-0.15
apr
-0.14
arto
-0.14
igo
-0.14
cos
-0.14
tan
-0.14
383
-0.14
ger
-0.13
POSITIVE LOGITS
intptr
0.16
onta
0.16
uintptr
0.15
vection
0.15
usto
0.15
ç¿Ķ
0.14
oen
0.14
usta
0.14
intf
0.14
_intf
0.14
Activations Density 0.070%