INDEX

Explanations

javadoc param annotations

The neuron activates on doc-block annotation syntax (stars, at-sign tags, parameter markers like “@param” and “$” variables, and inline numbers) in code comments.

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

 didn

-1.28

 invers

-1.27

are

-1.27

 sali

-1.23

”),

-1.23

:&

-1.21

 ving

-1.20

 wouldn

-1.20

 mati

-1.20

 trent

-1.19

POSITIVE LOGITS

its

1.45

 vēl

1.38

MAXN

1.29

 chcą

1.28

 vairāk

1.23

 szuka

1.23

providedIn

1.22

 pertenec

1.21

 besonders

1.21

For

1.21

Activations Density 0.016%