INDEX

Explanations

measurement units and scientific notation

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

</h2>

-1.90

':{

-1.75

鑄

-1.73

ところで

-1.70

みると

-1.67

 amortecedor

-1.66

 biß

-1.63

铼

-1.61

 Befes

-1.61

UVWXYZ

-1.60

POSITIVE LOGITS

to

1.96

𓐍

1.71

ЛОВ

1.58

жар

1.55

of

1.54

your

1.53

often

1.52

ССР

1.47

ол

1.47

but

1.39

Activations Density 0.000%