INDEX

Explanations

tokens, word, and character estimations

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

过

0.40

твы

0.39

пля

0.38

 Singing

0.37

াইল

0.37

 кише

0.36

 نقدم

0.36

க்கொண்டு

0.35

 QFile

0.35

 didReceive

0.35

POSITIVE LOGITS

roughly

0.58

 fractions

0.57

 word

0.55

 roughly

0.54

word

0.53

 token

0.50

token

0.47

 fraction

0.47

 tokens

0.47

fraction

0.47

Activations Density 0.038%