INDEX

Explanations

code delimiters ({}:,.)

The neuron strongly activates on standalone numeric literals (digits) in code.

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

for

-1.64

 those

-1.50

by

-1.34

-1.27

"}}>

-1.27

\\

-1.27

the

-1.27

⌉

-1.25

˗

-1.25

POSITIVE LOGITS

怎么回事

1.66

 rafraî

1.64

 refroid

1.63

 verrou

1.63

 beneficiario

1.62

 banyo

1.62

 récompense

1.61

 einzige

1.59

 uniquement

1.53

Tentang

1.52

Activations Density 0.181%