INDEX

Explanations

either/or options

It fires on prominent topical/content words and key informative nouns (tokens that mark main ideas or important concepts in a passage).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

:["

0.40

 besonders

0.40

等地

0.40

 especialmente

0.39

 असले

0.39

などが

0.38

痈

0.37

adang

0.37

など

0.36

尤其

0.36

POSITIVE LOGITS

—

0.78

 either

0.70

either

0.70

—

0.69

–

0.68

Either

0.64

albeit

0.60

 Either

0.59

 entweder

0.56

--

0.55

Activations Density 0.079%