INDEX
Explanations
names of cities in the UK
proper nouns related to specific locations and names
New Auto-Interp
Negative Logits
gerald
-0.82
ebin
-0.82
orter
-0.80
urtles
-0.79
skelet
-0.74
emort
-0.72
eat
-0.70
indust
-0.70
acci
-0.70
bour
-0.69
POSITIVE LOGITS
Cardiff
0.97
Swansea
0.94
Bradford
0.70
Walking
0.69
Shields
0.69
ength
0.68
BMC
0.66
Regener
0.66
Takeru
0.65
Warsaw
0.65
Activations Density 0.020%