INDEX

Explanations

No Explanations Found

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

😛

0.84

 malicious

0.79

😚

0.76

 harmful

0.74

 রোববার

0.72

🐽

0.72

 recreational

0.70

 vouchers

0.69

🔛

0.69

 😂😂

0.69

POSITIVE LOGITS

 Process

1.67

 Work

1.59

 Approach

1.58

 Role

1.56

 Support

1.56

 Needs

1.55

 Poss

1.53

 Setup

1.52

 Compet

1.52

 Context

1.52

Activations Density 6.844%

No Known Activations