INDEX

Explanations

programming keywords and syntax

The neuron detects code lines that import or include external modules or libraries (e.g., import, require, #include, using namespace).

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

is

-1.76

of

-1.51

we

-1.50

 siempre

-1.48

เป็น

-1.46

顎

-1.45

有时候

-1.44

 Pfar

-1.43

ก็

-1.41

POSITIVE LOGITS

columnwidth

1.63

 сообщили

1.63

⍺

1.63

ύ

1.63

ragal

1.61

 retirar

1.60

𝐱

1.59

 inalámbrica

1.59

voici

1.57

 FICTION

1.55

Activations Density 0.137%