INDEX

Explanations

semantic features

The neuron responds to high‐frequency function words (like “is,” “that,” “but,” “you,” “to,” etc.)—including their equivalents in Indonesian—i.e. grammatical “stop” words.

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

תודה

-1.43

 cortinas

-1.27

Tahun

-1.26

敍

-1.23

 sesiones

-1.23

していました

-1.23

tranh

-1.21

쎄

-1.20

Karakteristik

-1.20

אין

-1.20

POSITIVE LOGITS

“

1.44

 also

1.32

ER

1.29

1.20

1.19

1.18

THE

1.14

на

1.14

1.12

is

1.11

Activations Density 0.001%