INDEX

Explanations

exploit, abuse or endanger children

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

ο

1.36

 fence

1.34

winner

1.32

 sanding

1.27

cale

1.26

Distance

1.23

 വേണ്ടി

1.20

artist

1.18

aik

1.17

 réservation

1.15

POSITIVE LOGITS

ﺰ

0.98

ักษณ์

0.98

 massif

0.95

 बल्

0.94

ﺬ

0.94

ovaniyu

0.94

0.90

^\

0.90

తు

0.89

 поту

0.86

Activations Density 0.002%