INDEX

Explanations

specific entities or standalone words

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

ра

1.66

1.35

اد

1.33

en

1.32

ियर्स

1.23

 راست

1.22

บาท

1.22

1.21

 ос

1.17

1.16

POSITIVE LOGITS

 hassle

1.51

కి

1.50

cwd

1.48

浦

1.39

slip

1.33

 খেলে

1.32

ㅢ

1.31

 zeich

1.31

 लोकसभा

1.27

 situasi

1.26

Activations Density 0.001%