INDEX

Explanations

test and check code

This neuron detects unit-testing code constructs, such as test framework includes (e.g. gtest, catch2), TEST/REGISTER macros, and other testing-related identifiers.

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

heureusement

-1.70

ྵ

-1.66

estión

-1.65

%),

-1.63

%);

-1.56

 Königin

-1.56

盗

-1.55

 kutoka

-1.55

 will

-1.53

 থেকে

-1.52

POSITIVE LOGITS

2.17

1.91

1.69

1.61

1.49

通常の

1.45

そりゃ

1.40

Doing

1.39

Activations Density 0.006%