INDEX
Explanations
proper names or references to a person named Ari
mentions of the name "Ari."
New Auto-Interp
Negative Logits
enegger
-0.78
nikov
-0.75
ding
-0.72
paralleled
-0.71
ãģį
-0.70
advertisement
-0.69
SIGN
-0.69
WARD
-0.69
limited
-0.68
ACTED
-0.67
POSITIVE LOGITS
Ari
1.03
zon
0.86
jit
0.84
anna
0.83
tera
0.82
zeb
0.82
ī
0.80
agons
0.78
asing
0.75
zona
0.75
Activations Density 0.007%