INDEX
Explanations
references to a specific sports team
references to the "Heat" team in various contexts
New Auto-Interp
Negative Logits
Mond
-0.73
ablishment
-0.70
Rockefeller
-0.65
Crossref
-0.65
ication
-0.64
ystem
-0.64
arge
-0.64
alia
-0.64
VICE
-0.63
dding
-0.62
POSITIVE LOGITS
Heat
1.34
Heat
1.26
hens
0.99
heat
0.97
waves
0.94
ILCS
0.90
seekers
0.88
wave
0.79
exch
0.76
Dolphins
0.75
Activations Density 0.006%