INDEX
Explanations
references to the city of Oxford
mentions of the University of Oxford
New Auto-Interp
Negative Logits
++++++++++++++++
-0.86
++++
-0.76
++++++++
-0.74
CVE
-0.74
selage
-0.73
////////
-0.71
SHIP
-0.69
quo
-0.69
RANT
-0.68
Magikarp
-0.66
POSITIVE LOGITS
shire
1.55
Circus
0.99
bridge
0.86
comma
0.84
hurst
0.84
Oxford
0.83
Square
0.81
Manor
0.80
ington
0.79
University
0.78
Activations Density 0.012%