INDEX

Explanations

last names after titles

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

ुद्ध

0.83

Akt

0.70

За

0.70

ReLU

0.70

Für

0.69

 logarithmic

0.68

 convolutional

0.67

Über

0.66

Про

0.65

蒟

0.65

POSITIVE LOGITS

 Davis

1.53

 Johnson

1.40

 Thompson

1.39

 Jones

1.38

 Miller

1.37

Davis

1.36

 Smith

1.34

 Wilson

1.32

 Henderson

1.29

 Williams

1.28

Activations Density 0.041%