INDEX
Explanations
proper nouns related to a person named Ari
mentions of the name "Ari."
New Auto-Interp
Negative Logits
ding
-0.77
enegger
-0.76
nikov
-0.71
limited
-0.70
paralleled
-0.70
advertisement
-0.68
eners
-0.68
ulhu
-0.67
íķ
-0.66
é¾
-0.66
POSITIVE LOGITS
Ari
0.92
zon
0.90
jit
0.86
zona
0.83
ī
0.82
anna
0.75
elle
0.75
Lens
0.74
Ģ
0.74
¢
0.74
Activations Density 0.009%