INDEX

Explanations

debunking false claims and ideas

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

明白了

0.42

 جانتے

0.42

埬

0.41

 यामुळे

0.41

Unexpected

0.40

 desconocido

0.39

 رموز

0.38

 неожидан

0.38

 Knowing

0.37

 remembered

0.37

POSITIVE LOGITS

 claim

1.36

 claims

1.35

 assertion

1.31

 behaupt

1.29

 assertions

1.27

 claiming

1.20

 notion

1.17

claims

1.15

 Claim

1.13

 Claims

1.09

Activations Density 0.041%