INDEX

Explanations

carb- words

The neuron detects occurrences of the letter sequence “carb” (as in carburetor, carbene, carbohydrate, 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

-2.63

л

-2.55

’，

-2.44

 sorta

-2.30

 hohe

-2.25

But

-2.22

ти

-2.22

ING

-2.22

甃

-2.13

referred

-2.11

POSITIVE LOGITS

驀

2.42

 unrelenting

2.36

 másik

2.30

国庆

2.28

膂

2.19

 menurun

2.13

the

2.13

他会

2.11

征服

2.11

ции

2.08

Activations Density 0.016%