INDEX

Explanations

recognizable word or phrase

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

А

1.94

 sous

1.80

اد

1.77

של

1.72

)*

1.69

 caravans

1.68

 sociedad

1.65

當地

1.64

 sandy

1.61

 encuentran

1.59

POSITIVE LOGITS

2.79

te

2.57

yta

2.46

xiety

2.40

kannya

2.28

zelfde

2.27

britannien

2.20

𝘇

2.20

ar

2.20

cą

2.19

Activations Density 0.189%