INDEX

Explanations

self-discovery and potential

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

pte

1.70

ﺔ

1.57

الت

1.56

িরা

1.55

nals

1.51



1.50

רים

1.50

 batsman

1.47

িৎ

1.46

ச்

1.45

POSITIVE LOGITS

 chuyện

1.37

 মধ্যে

1.36

ثت

1.34

 conto

1.31

ات

1.31

Ꭳ

1.31

 entirety

1.29

 antagon

1.27

honey

1.25

𝚝

1.20

Activations Density 0.095%