INDEX

Explanations

proper nouns after punctuation

apostrophe-based word forms such as contractions and possessives.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

៦

0.26

២

0.25

៤

0.23

១

0.23

猀

0.23

 또한

0.22

៥

0.22

 включа

0.21

༥

0.21

๑

0.21

POSITIVE LOGITS

 Venetian

0.20

 George

0.19

 state

0.18

 Curry

0.17

 Austen

0.17

 Gregorian

0.17

 Douglas

0.17

 Vermont

0.17

 Venture

0.17

 Tudor

0.17

Activations Density 2.563%