INDEX

Explanations

in followed by a descriptor

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

ता

1.57

 comboBox

1.44

 społec

1.41

্লিকেশন

1.41

 когато

1.33

 mitigate

1.31

۹

1.30

년에

1.29

会议

1.26

ທ່ານ

1.25

POSITIVE LOGITS

Honestly

1.19

 ナイス

1.17

shock

1.17

kale

1.13

 utmost

1.09

カリ

1.09

न्यू

1.08

意思是

1.08

Chocolate

1.06

kook

1.05

Activations Density 0.185%