INDEX

Explanations

explaining 'how' and 'about'

This neuron primarily detects the section‐title token “About” (as used in headers or navigation labels).

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

and

-1.66

).

-1.48

 also

-1.43

="

-1.25

 среда

-1.24

 them

-1.22

also

-1.21



-1.19

):

-1.19

"]:

-1.17

POSITIVE LOGITS

ducers

1.90

criminate

1.58

its

1.48

estimable

1.47

つた

1.45

什么时候

1.42

 oferece

1.40

 about

1.39

 necessary

1.38

我还是

1.38

Activations Density 0.022%