INDEX
Explanations
HTML entities, specifically non-breaking spaces
New Auto-Interp
Negative Logits
ibri
-0.20
Inst
-0.18
eler
-0.16
ôi
-0.15
Verb
-0.14
INST
-0.14
Inst
-0.14
byt
-0.14
ucht
-0.14
INST
-0.14
POSITIVE LOGITS
Gesture
0.15
emm
0.15
857
0.15
Crescent
0.14
PAD
0.14
imd
0.14
Fro
0.13
ideon
0.13
CharSequence
0.13
PrototypeOf
0.13
Activations Density 0.001%