INDEX

Explanations

technical terms and concepts

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

ع

2.66

ت

2.33

ת

2.16

ет

1.95

 χρόνο

1.94

িপুর

1.93

tter

1.92

ﻟ

1.91

던

1.77

ει

1.77

POSITIVE LOGITS

 Juga

1.69

1.64

cht

1.59

但这

1.59

férences

1.55

 Hanya

1.49

broom

1.48

Мы

1.46

지

1.45

 Incorrect

1.45

Activations Density 0.127%