INDEX

Explanations

tokenization and vocabulary

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

淵

0.42

俬

0.42

cket

0.42

Donnell

0.41

 srcset

0.41

 Traction

0.41

 રાશિ

0.40

кугӀ

0.39

 ресу

0.39

 Yvonne

0.39

POSITIVE LOGITS

 vocabulary

0.82

 vocab

0.82

 tokens

0.80

 sequences

0.80

 tokenizer

0.79

 Vocabulary

0.78

 Sentence

0.76

 token

0.76

 sentence

0.75

GPT

0.74

Activations Density 0.121%