INDEX
Explanations
elements of storytelling and narrative structure
New Auto-Interp
Negative Logits
but
-0.36
but
-0.31
nhưng
-0.26
maar
-0.23
αλλά
-0.23
ä½Ĩ
-0.23
_but
-0.23
-but
-0.23
But
-0.22
íķĺì§Ģë§Į
-0.22
POSITIVE LOGITS
nonetheless
0.71
nevertheless
0.66
Nevertheless
0.54
Nonetheless
0.50
none
0.48
Nevertheless
0.46
none
0.34
None
0.34
NONE
0.32
noch
0.32
Activations Density 0.341%