INDEX

Explanations

allow enabling something

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

 lured

1.46

 collars

1.43

 plaques

1.41

’

1.38

べて

1.28

 cans

1.28

 singled

1.27

 sardines

1.26

 villes

1.25

িতে

1.23

POSITIVE LOGITS

tı

2.27

tır

2.23

tte

2.09

да

2.05

2.02

tter

1.93

 intérieure

1.86

tidak

1.86

т

1.80

tur

1.73

Activations Density 0.191%