INDEX

Explanations

past actions or events

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

 actively

1.13

非常に

1.13

 extremamente

1.13

 completely

1.09

 extremely

1.06

 estremamente

1.05

 매우

1.03

 totally

1.01

 continuously

0.97

 heavily

0.97

POSITIVE LOGITS

 coax

0.79

 conj

0.63

 लिहाजा

0.59

gulp

0.59

 दुरु

0.58

 sprouting

0.57

 hoisting

0.57

 Summon

0.56

 dutiful

0.55

 dogged

0.54

Activations Density 0.107%