INDEX

Explanations

moments

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hode

-0.73

arb

-0.73

Stair

-0.69

ラダ

-0.67

 recrutement

-0.64

uza

-0.63

boost

-0.63

 Packed

-0.63

aula

-0.62

从未

-0.61

POSITIVE LOGITS

 moments

2.05

 moment

1.77

 Moments

1.76

moment

1.67

 Moment

1.64

moments

1.57

Moment

1.57

Moments

1.47

 momenti

1.32

 Momente

1.30

Activations Density 0.049%