INDEX

Explanations

contradicts or implements

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 alguna

0.47

 algum

0.46

 algún

0.44

いくつかの

0.43

いくつか

0.42

 nogen

0.41

幾個

0.41

LLA

0.39

 বেশকিছু

0.39

اتھن

0.38

POSITIVE LOGITS

 عادة

0.48

 usually

0.42

 traditionally

0.42

 typically

0.42

"[

0.41

通常

0.41

 обычно

0.40

 genellikle

0.40

ಜೆ

0.39

 Traditionally

0.39

Activations Density 0.006%

No Known Activations