INDEX

Explanations

to be helpful and harmless

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

टर

1.40

檛

1.30

 awọn

1.27

चुनाव

1.26

ﺽ

1.26

सभी

1.23

ﻕ

1.22

अंग्रे

1.18

 administrativos

1.16

ﻉ

1.16

POSITIVE LOGITS

ни

1.47

ној

1.38

ิ

1.31

 admirably

1.29

ik

1.28

ح

1.26

andır

1.24

ри

1.23

nél

1.23

دق

1.22

Activations Density 0.084%