INDEX

Explanations

code syntax and operators

The neuron is triggered by code tokens that carry semantic content (identifiers like variable and type names and literal values such as numbers or char constants).

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

{"

-0.89

「

-0.87

]["

-0.84

 ".";

-0.83

 "*",

-0.77

كوم

-0.77

\""

-0.75

適用

-0.75

")

-0.73

「

-0.72

POSITIVE LOGITS

'\

1.58

='

1.57

1.52

‘

1.49

'@

1.43

-'

1.43

('

1.37

、『

1.32

'$

1.28

#'

1.27

Activations Density 0.021%