INDEX

Explanations

programming code constructs

This neuron activates on code identifiers (e.g. function, method, class, or variable names).

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

 таких

-1.46

mittelt

-1.41

我们的

-1.39

我們的

-1.38

 такой

-1.34

 таким

-1.28

។

-1.27

 forthwith

-1.27

我們

-1.26

新的

-1.25

POSITIVE LOGITS

to

2.19

2.16

the

2.03

and

1.86

 actionTypes

1.73

for

1.65

\&

1.65

in

1.62

1.56

\_

1.56

Activations Density 0.303%