INDEX

Explanations

code documentation comments

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

وأ

2.55

ak

2.54

પ

2.39

más

2.38

für

2.29

ust

2.27

ون

2.26

و

2.15

 excepción

2.12

bygg

2.10

POSITIVE LOGITS

cknowled

2.77

sure

2.52

ske

2.37

மாக

2.31

いますが

2.30

ｅ

2.29

엥

2.26

本発明

2.23

 crowns

2.21

 કરીને

2.20

Activations Density 0.001%