INDEX

Explanations

World Wars and war concepts

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

০০

2.10

años

1.94

 hostility

1.79

 arrogance

1.79

urization

1.78

 cattle

1.75

iénd

1.74

قف

1.73

я

1.64

 powerfully

1.63

POSITIVE LOGITS

 waged

2.31

 footing

1.64

்ட்

1.60

ស៊ី

1.59

্ল্ড

1.55

ंग

1.50

ర్

1.48

स्परिक

1.46

चलिए

1.45

riors

1.43

Activations Density 0.070%