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

shore

0.70

)**

0.65

textbf

0.65

dashboard

0.64

pex

0.64

Dashboard

0.60

 følge

0.60

**

0.58

:**

0.57

:[

0.57

POSITIVE LOGITS

 Humanitarian

0.91

 Publish

0.85

 ambiguities

0.79

 debilitating

0.77

 facilitators

0.76

 nefarious

0.76

 assassination

0.76

 Facilit

0.75

 humanitarian

0.73

 Purchasing

0.73

Activations Density 0.017%

No Known Activations