INDEX
Explanations
phrases related to time duration and short timeframes
New Auto-Interp
Negative Logits
_least
-0.15
fred
-0.14
ToFront
-0.14
füh
-0.14
ingt
-0.13
igel
-0.13
mắt
-0.13
byn
-0.13
onal
-0.13
ascript
-0.13
POSITIVE LOGITS
span
0.61
span
0.43
Span
0.42
Span
0.39
spans
0.38
space
0.37
-span
0.37
matter
0.34
(span
0.32
_span
0.31
Activations Density 0.082%