INDEX

Explanations

✨ emoji highlighting positive or attractive content

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

1.13

야

1.10

 размер

1.10

ல்

1.09

1.08

1.07

xie

1.05

csv

1.05

ung

1.04

 libri

1.01

POSITIVE LOGITS

 marquée

1.40

đer

1.36

}$&$-

1.29

FFER

1.28

 intense

1.27

 caucus

1.25

 facilité

1.22

 tempHeader

1.20

/−

1.19

 trinity

1.18

Activations Density 0.004%