INDEX
Explanations
verbs related to existence or presence
New Auto-Interp
Negative Logits
stime
-0.15
едж
-0.15
ImageData
-0.14
asia
-0.14
Yates
-0.14
ichi
-0.13
idia
-0.13
обол
-0.13
braco
-0.13
ILING
-0.13
POSITIVE LOGITS
able
0.30
using
0.21
sure
0.20
aware
0.19
currently
0.18
considering
0.18
are
0.18
comfortable
0.18
doing
0.18
unable
0.18
Activations Density 0.197%