INDEX

Explanations

constructor calls with arguments

The neuron fires on identifiers used as arguments inside parentheses in code calls (e.g. parameters passed to super(), methods, or constructors).

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

be

-1.94

is

-1.59

 then

-1.47

 also

-1.36

 justamente

-1.27

zzet

-1.20

 gerade

-1.16

ELTS

-1.16

瞥

-1.15

 dát

-1.12

POSITIVE LOGITS

 multicolore

1.41

энер

1.34

 conster

1.31

 taal

1.30

 flexibles

1.28

 batata

1.26

 illustratie

1.24

ubehör

1.23

istió

1.23

 rasg

1.22

Activations Density 0.008%