INDEX
Explanations
mentions of "Jefferson" and "Franklin" in the text
New Auto-Interp
Negative Logits
ture
-0.15
ISIBLE
-0.15
apur
-0.14
ĶåĽŀ
-0.14
lette
-0.14
/thread
-0.14
ÏĦεÏģ
-0.14
ÌĪ
-0.13
ì
-0.13
.compiler
-0.13
POSITIVE LOGITS
ian
0.16
ukt
0.15
utter
0.15
ikan
0.14
sembl
0.14
s
0.14
ysi
0.14
m
0.13
iku
0.13
ians
0.13
Activations Density 0.004%