INDEX
Explanations
geographic and cultural references specific to Hungary
New Auto-Interp
Negative Logits
clin
-0.16
td
-0.15
ting
-0.15
ti
-0.15
eron
-0.15
ess
-0.15
-Clause
-0.14
æ³ķéĻ¢
-0.14
constraint
-0.14
eros
-0.14
POSITIVE LOGITS
ekil
0.17
.sz
0.15
киÑĪ
0.15
asher
0.14
undos
0.14
ipel
0.14
decrypt
0.14
jem
0.14
amik
0.14
arta
0.13
Activations Density 0.083%