INDEX
Explanations
mentions of the location "Oklahoma"
references to the state of Oklahoma
New Auto-Interp
Negative Logits
lore
-0.73
Di
-0.70
âĶĢâĶĢ
-0.69
docking
-0.69
café
-0.68
droid
-0.67
df
-0.65
uria
-0.64
harbour
-0.64
learnt
-0.64
POSITIVE LOGITS
Oklahoma
3.63
Tulsa
2.52
lahoma
2.46
Kansas
2.03
Arkansas
1.97
Kansas
1.89
Alabama
1.83
Wichita
1.76
Oregon
1.76
Iowa
1.74
Activations Density 0.015%