INDEX
Explanations
mentions of being a fan of something
instances of the word "fan" and related fan expressions
New Auto-Interp
Negative Logits
apeake
-0.81
muddy
-0.68
ENCY
-0.66
eneg
-0.66
akespe
-0.66
ateral
-0.64
Osc
-0.64
unfocusedRange
-0.63
Morning
-0.59
terday
-0.59
POSITIVE LOGITS
atical
1.42
atics
1.17
fare
1.04
boys
1.02
atically
1.01
club
0.98
fiction
0.97
artist
0.96
atic
0.91
boy
0.87
Activations Density 0.020%