INDEX

Explanations

command output numbers

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

 vigente

1.28

enn

1.26

 زیرا

1.24

𝗍

1.23

 mida

1.20

אם

1.20

ations

1.19

據

1.19

那就

1.19

at

1.18

POSITIVE LOGITS

此之外

1.74

bdb

1.63

नाथन

1.50

dört

1.48

lemen

1.47

backs

1.41

dling

1.40

turtle

1.35

blers

1.34

 grafted

1.30

Activations Density 0.002%