INDEX

Explanations

and conditions

The neuron fires on boilerplate legal/license text, especially spotting the “terms and conditions” phrasing in software license headers.

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

its

-1.30

mga

-1.11

-1.10

 सेमी

-1.09

 các

-1.03

''

-1.03

 เว

-1.03

'';

-1.03

)':

-1.02

 Matters

-1.01

POSITIVE LOGITS

 their

2.19

Their

1.69

 jejich

1.68

 Their

1.59

 их

1.55

 їх

1.53

 această

1.38

 навіть

1.37

appliquer

1.34

 उनके

1.34

Activations Density 0.374%