INDEX
Explanations
references to historical events and figures, particularly related to slavery and cultural history
New Auto-Interp
Negative Logits
/apt
-0.16
Dak
-0.16
ipt
-0.15
oma
-0.15
ukes
-0.15
Wax
-0.15
μμ
-0.14
aden
-0.14
attendance
-0.14
Verfüg
-0.14
POSITIVE LOGITS
_defaults
0.15
ancient
0.15
utsch
0.14
medieval
0.14
idla
0.14
uds
0.14
usp
0.14
åĭ
0.13
çĵ¶
0.13
вÑĸк
0.13
Activations Density 0.626%