INDEX

Explanations

during specific times or periods

The main thing this neuron does is detect references to specific time periods or operating hours (e.g., “during,” “outside of these hours,” “normal office hours,” “non-business 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

in

-1.60

duced

-1.45

 selalu

-1.42

჻

-1.38

🏟

-1.38

 iyong

-1.34

 soldat

-1.33

 だっ

-1.32

 candidat

-1.30

躄

-1.30

POSITIVE LOGITS

 times

1.46

時候

1.45

 periods

1.41

 days

1.34

 мы

1.33

 January

1.31

1.30

 winter

1.30

そのため

1.27

 weeks

1.25

Activations Density 0.042%