INDEX

Explanations

dialogs and modals

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

agh

0.44

ong

0.38

lst

0.36

ived

0.36

iaz

0.35

זר

0.35

Ein

0.35

dummy

0.35

mand

0.34

 directly

0.34

POSITIVE LOGITS

 accessibility

0.86

 Accessibility

0.79

Accessibility

0.70

accessibility

0.69

 accesible

0.67

Accessible

0.66

 Accessible

0.63

 accessible

0.61

accessible

0.61

 accessibles

0.57

Activations Density 0.000%