INDEX

Explanations

week or weeks

The neuron flags references to temporal expressions—mentions of days, weeks, weekends, dates, and times.

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

が

-1.46

 dié

-1.42

 genoux

-1.40

-1.34

 caoutchouc

-1.30

 最后

-1.29

 lópez

-1.27

怎么做

-1.27

zyn

-1.27

𓍊

-1.26

POSITIVE LOGITS

it

1.55

 possibly

1.54

 should

1.51

 somebody

1.45

 bring

1.45

 hatten

1.41

 describes

1.38

an

1.34

 include

1.34

 aufgrund

1.31

Activations Density 0.016%