INDEX

Explanations

numbers followed by "are excellent"

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

newNode

0.35

ऐसे

0.34

ల్ని

0.33

alk

0.33

ihu

0.33

archiwizowane

0.32

attia

0.32

iono

0.32

ｄ

0.32

abb

0.32

POSITIVE LOGITS

 anderen

0.39

 collaborate

0.39

 دوسروں

0.38

 sonst

0.37

 dehors

0.36

 الآخر

0.36

Stim

0.35

 others

0.35

 quid

0.35

 elsewhere

0.34

Activations Density 0.051%