INDEX
Explanations
text segments that contain punctuation marks, particularly periods
New Auto-Interp
Negative Logits
rzy
-0.16
elman
-0.15
Lad
-0.14
504
-0.14
sposób
-0.14
Mandal
-0.13
_UNDEF
-0.13
ive
-0.13
èIJ
-0.13
Friedman
-0.13
POSITIVE LOGITS
ervo
0.17
ijn
0.16
ollision
0.16
QObject
0.14
RuntimeObject
0.14
ourcem
0.14
rame
0.14
îł
0.14
uer
0.14
Mime
0.14
Activations Density 0.002%