INDEX

Explanations

intrinsic characteristics

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

ppa

0.39

zá

0.38

moz

0.36

 kiss

0.36

Sto

0.33

 opposites

0.33

 conglomer

0.33

('-',

0.32

(-(

0.32

ppw

0.32

POSITIVE LOGITS

 little

0.56

little

0.50

 functional

0.47

Ӹ

0.47

Functional

0.45

្ន

0.45

intrinsic

0.45

固有

0.44

 intrinsic

0.43

 sedikit

0.43

Activations Density 0.036%