INDEX
Explanations
references to a sports team named "Leafs"
mentions of the Toronto Maple Leafs
New Auto-Interp
Negative Logits
esters
-0.76
nels
-0.73
isites
-0.72
swick
-0.69
inges
-0.69
enegger
-0.68
alian
-0.67
esson
-0.66
schild
-0.66
anke
-0.65
POSITIVE LOGITS
Leafs
1.04
FC
0.76
Leaf
0.70
uten
0.69
pora
0.69
onic
0.67
mania
0.67
¬¼
0.65
Yog
0.65
chedel
0.64
Activations Density 0.017%