INDEX

Explanations

just beneath, far, majority

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

𝐒

1.37

𝕊

1.27

𝗦

1.26

ہوری

1.23

 einzel

1.22

ээ

1.22

 ฝึก

1.20

 සෑම

1.20

 principalmente

1.20

 rigidly

1.19

POSITIVE LOGITS

lier

0.88

bow

0.87

welling

0.87

ớt

0.86

otoxic

0.86

iere

0.84

γω

0.82

oliko

0.81

andingan

0.81

olen

0.81

Activations Density 0.149%