INDEX

Explanations

I introducing author's explanations or intents

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

вший

0.51

вшие

0.48

мовір

0.43

াপিত

0.41

ው

0.40

وە

0.40

ುತ್ತದೆ

0.39

ваемых

0.39

[];

0.38

malıdır

0.37

POSITIVE LOGITS

am

0.86

 want

0.68

 хочу

0.65

 have

0.63

 tenho

0.61

 tengo

0.61

 vreau

0.60

 دارم

0.59

 estoy

0.58

 ام

0.57

Activations Density 0.020%