INDEX

Explanations

programming objects

The neuron activates on mentions of programming “objects” or “models” (e.g. object(s), models) in code or data schemas.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

if

-1.73

 triliun

-1.69

 pemasaran

-1.67

 their

-1.59

one

-1.58

 enormous

-1.45

 yeme

-1.44

пература

-1.42

any

-1.41

ggiata

-1.40

POSITIVE LOGITS

1.52

1.47

"]);

1.44

"}}>

1.43

 essas

1.41

forty

1.39

fifty

1.38

 mere

1.37

がこの

1.34

Activations Density 0.004%