INDEX
Explanations
gerunds and present participles
New Auto-Interp
Negative Logits
shan
-0.17
çĵ¶
-0.16
sch
-0.16
LOTS
-0.16
sert
-0.15
robat
-0.15
aras
-0.14
scri
-0.14
ing
-0.14
smith
-0.14
POSITIVE LOGITS
haus
0.21
elli
0.21
ope
0.17
redient
0.17
encies
0.17
enuity
0.17
redients
0.16
estion
0.16
hausen
0.16
dÃŃ
0.16
Activations Density 0.073%