INDEX

Explanations

friendly polite helpful

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

BOLD

0.46

 απαι

0.41

 defy

0.41

 bold

0.41

 defied

0.40

 controversial

0.39

 audacious

0.39

rigid

0.39

 elektromagnet

0.39

रोध

0.39

POSITIVE LOGITS

 friendliness

1.34

 friendly

1.27

 welcoming

1.20

 smiling

1.10

 courteous

1.10

 Friendly

1.09

 polite

1.08

 cheerful

1.06

 smiley

1.06

 smile

1.04

Activations Density 0.022%