INDEX

Explanations

Go code keywords and types

The neuron strongly activates on the Go pointer‐type asterisk (“*”) token, i.e. wherever a pointer receiver or pointer type is declared.

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

-1.84

 many

-1.66

 literalmente

-1.47

田市

-1.34

队友

-1.34

-1.33

einander

-1.31

ologists

-1.27

 tuvieron

-1.25

POSITIVE LOGITS

of

2.44

หรือ

1.70

 jego

1.61

衽

1.58

 резулта

1.58

gamon

1.57

ᐕ

1.56

 tajem

1.55

 تحميل

1.55

Må

1.54

Activations Density 0.002%