INDEX

Explanations

No Explanations Found

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

 Probe

0.40

Don

0.38

One

0.38

它

0.37

 Read

0.37

Probe

0.36

Wake

0.34

Convert

0.33

Eat

0.33

 До

0.33

POSITIVE LOGITS

 cautious

0.43

 ===============

0.41

umbia

0.40

 chiff

0.40

 cloths

0.40

 unsurprisingly

0.40

 চৌধ

0.39

лізу

0.39

 industrious

0.39

 chubby

0.38

Activations Density 0.000%

No Known Activations