INDEX

Explanations

machine learning

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

Reject

0.73

 शॉट

0.64

 Reject

0.64

 солдат

0.63

Album

0.63

該

0.63

reject

0.63

Guests

0.62

 Glory

0.62

딱

0.60

POSITIVE LOGITS

 analytics

1.50

 robotics

1.42

 neuroscience

1.36

 genomics

1.35

 informatics

1.33

 cybersecurity

1.33

 modeling

1.30

 radiology

1.30

 forensics

1.28

omics

1.27

Activations Density 0.964%