INDEX

Explanations

filtering and pruning data

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

গঞ্জে

0.45

变革

0.45

 بشكل

0.44

 hän

0.43

 कंध

0.43

গঞ্জ

0.42

Downtown

0.42

 успеха

0.42

 një

0.41

 institución

0.41

POSITIVE LOGITS

 original

0.57

 filtered

0.53

 prune

0.52

 datasets

0.50

original

0.50

 pruned

0.48

 filtering

0.47

ሶች

0.46

 output

0.45

られた

0.45

Activations Density 0.105%