INDEX

Explanations

code syntax and keywords

The neuron flags code tokens involved in bringing in external files or modules (e.g. import/require/include 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

-1.73

<blockquote>

-1.66

 hindurch

-1.63

-1.61

-1.59

—

-1.59

-1.56

-1.53

''

-1.50

POSITIVE LOGITS

 ſont

1.73

of

1.67

 sécher

1.59

 alſo

1.48

 akhirnya

1.45

㍉

1.44

bánh

1.43

 theſe

1.40

 ſhe

1.37

бору

1.37

Activations Density 0.044%