INDEX

Explanations

code identifiers and operators

The neuron activates on programming identifiers—names of variables, functions, classes, constants, etc.—inside code snippets.

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

 bicicletas

-1.37

 agricultores

-1.30

kontroll

-1.29

If

-1.26

angkap

-1.25

tyg

-1.24

brett

-1.24

detek

-1.24

tarta

-1.24

 altijd

-1.23

POSITIVE LOGITS

1.25

それでは

1.24

not

1.22

味付け

1.19

それだけ

1.17

론

1.16

1.15

ra

1.14

 پو

1.14

Activations Density 0.001%