INDEX
Explanations
sentences or clauses that end with a period
sentences that express a high frequency or intensity of punctuation
New Auto-Interp
Negative Logits
ing
-0.73
)";
-0.72
)");
-0.72
Tig
-0.70
lue
-0.69
)»
-0.69
"]
-0.69
bied
-0.68
"]}
-0.68
Vign
-0.67
POSITIVE LOGITS
.
1.58
/\.
1.14
.\
0.97
(.
0.93
:✨
0.91
_.
0.91
٫
0.89
','.
0.89
('.0.84
/**/*.
0.84
Activations Density 0.156%