INDEX
Explanations
references to gelatin or gel-like substances
New Auto-Interp
Negative Logits
egers
-0.18
mares
-0.15
llu
-0.15
iais
-0.15
fulness
-0.15
essed
-0.15
ionale
-0.15
er
-0.15
leurs
-0.15
ç´
-0.14
POSITIVE LOGITS
atin
0.33
ignite
0.22
ato
0.21
ateria
0.21
ATO
0.19
ände
0.19
atos
0.18
uid
0.18
antine
0.17
alin
0.17
Activations Density 0.004%