INDEX

Explanations

computing sums

The neuron fires whenever it sees the word “sum” (e.g. as a variable or function name in code).

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

?”

-2.92

 pomi

-2.33

).”

-2.30

 producenta

-2.13

 listop

-2.11

 całym

-2.05

 paździer

-2.03

 โดย

-1.98

”:

-1.95

 pokud

-1.93

POSITIVE LOGITS

2.48

2.38

2.31

2.20

2.13

_{

2.05

1.95

过年

1.88

ung

1.85

Activations Density 0.006%