INDEX

Explanations

text splitting chunks

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

ResponseBody

0.38

عين

0.38

äden

0.36

礽

0.36

יוחד

0.35

ність

0.35

いった

0.35

pley

0.35

Forty

0.34

 Garry

0.34

POSITIVE LOGITS

 delimiter

0.38

 delimiters

0.33

⅜

0.33

٣

0.32

 व्यक्त

0.32

isPreview

0.31

 boilerplate

0.31

३

0.31

amsmath

0.30

avam

0.30

Activations Density 0.002%