INDEX

Explanations

prints JSON or other output

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

1.53

 Improves

1.42

1.38

1.37

 Improved

1.34

ח

1.31

 Describes

1.27

 Indexes

1.26

 Earrings

1.24

 Annals

1.23

POSITIVE LOGITS

1.59

ul

1.41

る

1.33

ो

1.23

at

1.20

 desolate

1.19

 harmonica

1.18

ו

1.17

었

1.17

น

1.15

Activations Density 0.011%