INDEX

Explanations

secret, hidden, unnoticed

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

杲

0.72

 സാഹചര്യ

0.71

 ಹೋ

0.69

 Vorder

0.69

ropy

0.66

štění

0.65

acart

0.64

stantially

0.63

 جمهور

0.62

াভাবিক

0.62

POSITIVE LOGITS

 hidden

4.34

hidden

3.75

Hidden

3.63

 Hidden

3.57

 concealed

3.30

 secret

3.18

 nascost

3.15

隐藏

3.10

 unnoticed

3.10

 invisible

3.01

Activations Density 0.770%