INDEX

Explanations

adding friends

The neuron fires on mentions of “friend” (especially in “add friend” or “friends” contexts).

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

镬

-1.51

🤐

-1.50

﹒

-1.46

🤤

-1.45

 bougies

-1.37

*</

-1.35

Mts

-1.32

度

-1.31

🤭

-1.30

🤪

-1.30

POSITIVE LOGITS

 other

1.49

nitř

1.41

who

1.38

المراجع

1.35

znego

1.34

鳢

1.32

ípio

1.30

1.29

Воспита

1.26

 fisuras

1.26

Activations Density 0.038%