INDEX

Explanations

code definition keywords

The neuron primarily detects numeric literals (integers or floating-point numbers) 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

 насељу

-1.56

 betrek

-1.43

Ketika

-1.41

することも

-1.38

Numerous

-1.38

 solche

-1.37

 These

-1.35

 dichos

-1.34

 into

-1.32

我們的

-1.31

POSITIVE LOGITS

who

1.95

how

1.51

 usado

1.35

('

1.34

منون

1.32

1.30

 maybe

1.30

来店

1.27

,’”

1.25

</h2>

1.23

Activations Density 0.023%