INDEX
Explanations
mentions of the country Afghanistan
references to Afghanistan and related topics
New Auto-Interp
Negative Logits
vous
-0.84
yss
-0.84
creen
-0.79
Hunt
-0.78
icles
-0.72
*/(
-0.70
constitu
-0.69
eton
-0.68
tower
-0.67
ection
-0.66
POSITIVE LOGITS
istan
1.18
ghan
1.13
Kabul
1.09
Afghan
1.07
Afghanistan
1.06
Afgh
1.02
Taliban
1.00
Afghans
1.00
Albania
0.98
Pakistan
0.89
Activations Density 0.018%