INDEX

Explanations

programming imports

The neuron strongly activates on lines that import external libraries or modules (i.e. “import …” statements).

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

-1.60

by

-1.55

 because

-1.44

now

-1.42

 these

-1.41

for

-1.41

 more

-1.40

 people

-1.40

 Since

-1.38

 Only

-1.38

POSITIVE LOGITS

↵

1.70

↵↵↵

1.48

↵↵

1.30

 faciliter

1.27

↵↵↵↵↵↵↵↵↵↵

1.25

 EVEN

1.23

↵↵↵↵↵↵↵↵↵↵↵

1.21

 diverses

1.18

NEVER

1.17

 många

1.16

Activations Density 0.017%