INDEX

Explanations

social commentary and comments

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

с

2.91

ع

2.56

ത്ഥ

2.49

ார்

2.33

ாட்ட

2.32

一个

2.31

ный

2.30

ра

2.27

lr

2.23

揆

2.23

POSITIVE LOGITS

कारों

3.22

다

2.76

년

2.65

्युनिकेशन

2.61

 heel

2.60

ʙ

2.56

বেশী

2.51

dar

2.51

transfected

2.50

년에

2.45

Activations Density 0.043%