INDEX

Explanations

later followed by action

The neuron flags temporal expressions—words and phrases that specify times, dates, or periods.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 each

-1.73

 것이

-1.47

灃

-1.43

 fiecare

-1.38

 sidste

-1.37

makeText

-1.34

 every

-1.32

our

-1.31

 this

-1.31

 yesterday

-1.30

POSITIVE LOGITS

of

1.78

暗い

1.69

 creó

1.52

読書

1.46

一辆

1.45

遊ぶ

1.38

僕も

1.36

着一个

1.34

 creando

1.33

そも

1.30

Activations Density 0.078%