INDEX
Explanations
mentions of a specific sports team
mentions of the "Eagles" (likely referring to a sports team)
New Auto-Interp
Negative Logits
icity
-0.76
stroke
-0.69
itionally
-0.65
glim
-0.64
adies
-0.64
redistributed
-0.63
reconc
-0.62
iera
-0.62
cles
-0.61
ement
-0.61
POSITIVE LOGITS
agles
1.00
sburg
0.97
Eagles
0.96
onian
0.78
RON
0.68
kamp
0.66
backer
0.63
mare
0.63
LECT
0.61
uth
0.61
Activations Density 0.006%