INDEX

Explanations

string formatting and code elements

The neuron fires on occurrences of function‐call syntax (an identifier immediately followed by an opening parenthesis).

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

 Если

-1.58

 ausgeführt

-1.46

 cũng

-1.43

 также

-1.42

 επίσης

-1.39

 також

-1.37

 Когда

-1.37

 Мне

-1.36

anmoins

-1.36

 Также

-1.36

POSITIVE LOGITS

 they

1.56

 being

1.55

not

1.29

鈎

1.27

 funktioniert

1.26

 when

1.24

 getting

1.23

got

1.23

1.21

 having

1.18

Activations Density 0.005%