INDEX
Explanations
the verb "be" in various forms and contexts
New Auto-Interp
Negative Logits
dorf
-0.16
urma
-0.15
REEN
-0.15
906
-0.15
elight
-0.15
èά
-0.15
assin
-0.14
-pop
-0.14
ĵ
-0.14
848
-0.13
POSITIVE LOGITS
utherford
0.14
followed
0.14
straw
0.14
Fres
0.14
Bu
0.14
sor
0.14
collage
0.13
Curt
0.13
Shield
0.13
Nicol
0.13
Activations Density 0.108%