INDEX

Explanations

marking significant points

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

piration

2.14

 laugh

1.96

್ಧ

1.95

 chuckle

1.89

quiera

1.76

nA

1.73

ں

1.72

 $*$-

1.71

箪

1.71

даря

1.70

POSITIVE LOGITS

ם

1.61

劃

1.49

sc

1.42

 Kurs

1.40

duke

1.40

 driveway

1.37

ेड

1.34

amp

1.34

일까지

1.33

ків

1.31

Activations Density 0.074%