INDEX

Explanations

"we are" followed by verb or preposition

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

 потер

0.85

🦳

0.82

اریخ

0.81

 cowardly

0.75

ágoras

0.75

 cyberpunk

0.74

 CTRL

0.74

 vores

0.74

褸

0.74

 Folgen

0.73

POSITIVE LOGITS

 engaged

0.81

 living

0.76

 into

0.75

 manufacturer

0.75

engaged

0.73

manufacturer

0.73

Given

0.72

living

0.72

 deeply

0.71

 given

0.71

Activations Density 0.001%