INDEX

Explanations

nn.Module and decoder definitions

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

apprent

0.44

 potash

0.37

ร

0.37

IfExists

0.37

飛

0.37

0.36

اب

0.36

șt

0.36

 logs

0.35

 logique

0.35

POSITIVE LOGITS

 Decoder

0.47

decoder

0.45

 decoder

0.42

dek

0.39

Decoder

0.38

Chy

0.38

rey

0.37

Dec

0.36

 деко

0.36

 চরণ

0.36

Activations Density 0.004%