INDEX
Explanations
the phrase "physical activity"
activity
New Auto-Interp
Negative Logits
Personensuche
-1.09
".
-0.98
$_"
-0.93
)”.
-0.90
):}
-0.86
?”,
-0.84
)":
-0.84
*}[
-0.83
),”
-0.82
?”.
-0.82
POSITIVE LOGITS
↵↵
0.91
A
0.79
I
0.77
<eos>
0.77
0.72
.
0.71
↵↵↵
0.69
e
0.66
G
0.65
↵
0.62
Activations Density 1.649%