INDEX

Explanations

independent viewpoint

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

--

0.41

paj

0.37

 neighbors

0.36

 Oral

0.35

<unused91>

0.35

 Neighbors

0.35

 Neigh

0.35

asat

0.35

--(

0.34

 ন্যা

0.34

POSITIVE LOGITS

にお

0.45

 individuals

0.41

individuals

0.39

Individuals

0.39

Asimismo

0.39

Indeed

0.38

indeed

0.38

ωσ

0.37

subdirectory

0.37

چنین

0.37

Activations Density 0.002%