INDEX

Explanations

the presence of `*`, `-`, or `[` characters following certain tokens

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

ский

1.29

ية

1.19

iej

1.12

টি

1.10

ements

1.09

৯

1.06

いた

1.05

ems

1.05

ism

1.02

↵

1.02

POSITIVE LOGITS

Bước

1.43

 Warum

1.36

 Governo

1.33

 Amerikan

1.31

 Banyak

1.30

 Romney

1.29

 Elmer

1.29

tional

1.27

 elde

1.27

 Rosberg

1.26

Activations Density 0.389%