INDEX

Explanations

map API

The neuron fires on code or text referring to maps (especially the token “map” or “maps” in mapping APIs).

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

 which

-1.59

’

-1.52

and

-1.38

所以我

-1.38

 których

-1.36

arsenal

-1.35

ếc

-1.33

("}");

-1.32

 takımı

-1.29

豺

-1.27

POSITIVE LOGITS

it

1.72

ஂ

1.56

 autorisation

1.51

①

1.51

Figure

1.44

 ouverture

1.42

④

1.41

賸

1.40

槼

1.39

 garantie

1.38

Activations Density 0.021%