INDEX
Explanations
references to a specific person, likely named "Reid"
mentions of the name "Reid."
New Auto-Interp
Negative Logits
andise
-1.03
omaly
-0.80
teenth
-0.76
ruciating
-0.75
eatures
-0.74
ILCS
-0.69
tips
-0.67
oppable
-0.67
tesy
-0.67
argon
-0.63
POSITIVE LOGITS
burgh
0.89
Reid
0.77
sburg
0.75
bro
0.75
igan
0.74
ety
0.72
elin
0.71
ifying
0.71
Mysteries
0.70
quist
0.68
Activations Density 0.023%