INDEX

Explanations

accessing list elements

The neuron strongly activates on code snippets where values are being accessed (via bracket‐indexing or dot‐property access) and then compared or tested for membership (e.g. ==, ===, “not in,” etc.).

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

 only

-1.40

it

-1.36

maksi

-1.30

not

-1.25

all

-1.19

了两

-1.16

two

-1.16

 just

-1.15

 alleen

-1.13

 який

-1.10

POSITIVE LOGITS

 distintas

1.42

different

1.39

比较好

1.34

 different

1.33

 distintos

1.32



1.27

änning

1.27

 различных

1.25

various

1.24

 jeweiligen

1.23

Activations Density 0.035%