INDEX

Explanations

class names and types

This neuron detects the names of imported classes or types (capitalized identifiers) in import/use statements.

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

 besonderes

-1.23

for

-1.23

 particular

-1.22

髭

-1.20

 Preisen

-1.18

bandcamp

-1.16

tvguide

-1.10

 Briefe

-1.09

 persön

-1.08

 numerosi

-1.08

POSITIVE LOGITS

 that

1.59

焢

1.34

 répon

1.31

 Kalimantan

1.30

ابراین

1.28

sieme

1.25

 AppCompatTheme

1.22

quelize

1.22

潜力

1.21

 """",

1.20

Activations Density 0.021%