INDEX

Explanations

class and label predictions

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

诋

0.47

 წყ

0.45

Ofer

0.43

രുവ

0.39

InteropServices

0.39

馆

0.38

রাষ্ট্রম

0.38

 πρόσ

0.38

Payroll

0.37

 تز

0.37

POSITIVE LOGITS

 labels

1.61

 label

1.47

labels

1.45

 Labels

1.41

 class

1.36

 classes

1.34

Labels

1.31

label

1.30

 Label

1.27

 классов

1.25

Activations Density 0.083%