INDEX
Explanations
mentions of specific place names related to sports teams or events
instances of "BO" in various contexts, likely indicating references to Boston
New Auto-Interp
Negative Logits
imental
-0.82
gew
-0.79
nikov
-0.78
uality
-0.76
geist
-0.73
icals
-0.73
alia
-0.72
iment
-0.72
mary
-0.71
itating
-0.71
POSITIVE LOGITS
BO
1.03
OTH
0.95
ARD
0.94
leans
0.94
OM
0.92
ARDS
0.91
OTS
0.87
OSE
0.86
oard
0.86
INC
0.85
Activations Density 0.005%