INDEX

Explanations

mathematical expressions

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

 this

-2.03

stridium

-1.49

那你

-1.46

now

-1.42

₂)

-1.41

ctiveness

-1.40

manın

-1.38

┍

-1.35

Pokud

-1.34

今回

-1.32

POSITIVE LOGITS

1.68

 they

1.67

<i>

1.62

它們

1.60

它们

1.58

地说

1.55

 каждого

1.43

种类

1.38

不夠

1.37

 ſhould

1.34

Activations Density 0.019%