INDEX

Explanations

aesthetic appeal and style

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

ból

2.64

ع

2.38

ت

2.36

 облег

2.09

ي

2.09

 abiert

2.03

تها

1.98

 обеспечения

1.98

 молод

1.95

𝚘

1.93

POSITIVE LOGITS

да

1.86

‎

1.63



1.61

 biographical

1.57

ю

1.55

 kink

1.52

 summar

1.48

 purview

1.48

εί

1.48

 bulky

1.45

Activations Density 0.006%