INDEX

Explanations

author initials preceded by punctuation

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

 YouTuber

0.21

 Tensor

0.20

 اضافه

0.19

=(

0.18

 హీరో

0.18

 Transformer

0.18

 KMeans

0.18

 Maschine

0.18

tfine

0.18

 Partizan

0.18

POSITIVE LOGITS

0.27

and

0.25

và

0.23

 आणि

0.22

et

0.22

 agus

0.22

և

0.22

и

0.21

 және

0.21

 এবং

0.21

Activations Density 0.023%