INDEX
Explanations
various expressions of acknowledgment and commentary in conversational context
Signals additional, related information
introducing additional points
New Auto-Interp
Negative Logits
']],
-0.72
endregion
-0.66
']):
-0.63
*/;
-0.61
/>";
-0.59
}],
-0.59
etheless
-0.59
ennom
-0.58
')):
-0.58
/>';
-0.57
POSITIVE LOGITS
forgot
0.99
BTW
0.96
顺便
0.95
btw
0.95
note
0.94
remember
0.91
FYI
0.88
BTW
0.85
speaking
0.84
FYI
0.83
Activations Density 0.170%