INDEX

Explanations

end of sentence starters

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

istro

0.59

unci

0.57

 כאשר

0.57

elesaian

0.57

 kerana

0.56

individuals

0.55

 beispielsweise

0.55

dise

0.54

 bowiem

0.53

～～

0.53

POSITIVE LOGITS

 Been

1.46

 Didn

1.42

Got

1.24

Been

1.24

 Gonna

1.23

 Hoping

1.23

 Took

1.22

 Looks

1.22

 Thought

1.21

 Couldn

1.21

Activations Density 0.151%