INDEX
Explanations
references to medium-sized entities or concepts
New Auto-Interp
Negative Logits
etik
-0.15
iaux
-0.15
phin
-0.15
withStyles
-0.15
286
-0.15
anter
-0.15
áo
-0.15
enames
-0.15
iger
-0.14
zen
-0.14
POSITIVE LOGITS
-sized
0.40
sized
0.40
Sized
0.30
-size
0.29
-term
0.28
-range
0.28
size
0.26
-large
0.25
ship
0.24
-priced
0.24
Activations Density 0.022%