INDEX

Explanations

function calls with parentheses

The neuron fires on identifiers immediately followed by an opening parenthesis, i.e. function or method calls.

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

and

-1.80

了些

-1.51

for

-1.48

 (!__

-1.20

 enkele

-1.19

了一会儿

-1.18

to

-1.15

مرار

-1.13

一抹

-1.13

 arşivlendi

-1.12

POSITIVE LOGITS

1.57

the

1.50

it

1.23

of

1.23

you

1.19

 Apos

1.16

ğından

1.16

ᴘ

1.13

méno

1.12

 propensity

1.11

Activations Density 0.003%