INDEX

Explanations

Monday through Friday

The neuron detects tokens that appear in business‐hours or scheduling sections—i.e. days, times, and numeric ranges specifying opening or operating hours.

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

 redondo

-1.60

 while

-1.41

сль

-1.40

淠

-1.38

 unangemessene

-1.34

 melakukannya

-1.33

 bancada

-1.31

 SEGU

-1.31

 joão

-1.31

 już

-1.31

POSITIVE LOGITS

as

1.43

to

1.33

1.29

躋

1.29

but

1.29

懟

1.27

ver

1.26

IA

1.24

man

1.23

ina

1.21

Activations Density 0.028%