INDEX

Explanations

function signatures and variable types

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

 common

1.28

 rejection

1.25

ih

1.22

 secure

1.21

 recognition

1.20

 extraction

1.20

د

1.19

 tread

1.16

 ком

1.15

 popular

1.12

POSITIVE LOGITS

์

1.36

esehatan

1.24

hostname

1.18

 budynku

1.17

toml

1.17

argmax

1.16

Kaynak

1.16

logn

1.16

 exponentes

1.16

cid

1.16

Activations Density 0.340%