INDEX

Explanations

"We" followed by auxiliaries or verbs

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

 kendini

0.59

其

0.58

当我

0.57

那你

0.56

 اخرى

0.54

你的

0.54

your

0.54

的同时

0.53

my

0.52

 उन्होंने

0.52

POSITIVE LOGITS

 можем

1.56

 ourselves

1.42

 pouvons

1.32

 знаем

1.26

 possiamo

1.25

 avons

1.23

 devons

1.19

 możemy

1.14

 máme

1.13

 dobbiamo

1.13

Activations Density 0.292%