INDEX
Explanations
phrases indicating duration or a long period of time
New Auto-Interp
Negative Logits
ÄįnÃŃk
-0.17
reater
-0.17
寸
-0.16
lsru
-0.16
edido
-0.15
rial
-0.15
ovich
-0.14
reature
-0.13
Bool
-0.13
lsi
-0.13
POSITIVE LOGITS
long
0.90
long
0.72
LONG
0.62
.long
0.61
-long
0.60
(long
0.56
Long
0.53
éķ¿
0.52
Long
0.52
_long
0.51
Activations Density 0.092%