INDEX
Explanations
mentions of the word "Guantanamo"
references to Guantanamo Bay
New Auto-Interp
Negative Logits
Riding
-0.67
buck
-0.67
orest
-0.66
vine
-0.66
ph
-0.66
hester
-0.65
Pony
-0.65
spir
-0.63
inator
-0.63
ph
-0.62
POSITIVE LOGITS
Guantanamo
3.81
Guant
3.36
detainee
2.40
detainees
2.38
anamo
1.88
Git
1.83
detention
1.56
interrogation
1.49
torture
1.39
interrog
1.37
Activations Density 0.025%