INDEX
Explanations
mentions of the word "Chin" or similar variations
references to a specific individual or the concept of "chin."
New Auto-Interp
Negative Logits
theless
-0.72
behavi
-0.72
bies
-0.70
Phant
-0.70
ICE
-0.67
éĹ
-0.64
andom
-0.64
ãĥ¤
-0.64
ionage
-0.63
CLASSIFIED
-0.63
POSITIVE LOGITS
atown
0.99
amen
0.90
acea
0.87
jiang
0.86
ooks
0.86
ook
0.83
uations
0.83
azo
0.81
kees
0.80
enged
0.79
Activations Density 0.039%