INDEX

Explanations

Negative character traits

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

 guer

0.66

 remodel

0.64

 renovations

0.64

 attiv

0.64

 rencont

0.64

 staining

0.63

 renov

0.61

व

0.60

vs

0.60

 pups

0.60

POSITIVE LOGITS

Pride

0.70

 complacency

0.67

Seat

0.63

Plate

0.63

骥

0.58

Treat

0.57

 complacent

0.57

Learning

0.56

骄

0.55

JUnit

0.54

Activations Density 0.027%