INDEX

Explanations

code structure with brackets

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

ר

0.41

lijke

0.41

ン

0.40

 של

0.40

 раствор

0.39

gång

0.39

ג

0.38

㗊

0.38

ремен

0.38

ttps

0.38

POSITIVE LOGITS

0.37

idx

0.34

 outperform

0.33

][

0.32

idx

0.32

 eléctrica

0.31

pt

0.31

 vect

0.31

 bipartite

0.31

Activations Density 0.092%