INDEX

Explanations

specific entities introduced by this

The neuron strongly responds to self-referential demonstrative language—especially the word “this.”

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

 trecut

-1.55

stricken

-1.50

➆

-1.48

and

-1.45

轱

-1.39

܃

-1.38

thodoxy

-1.36

pady

-1.34

いしい

-1.34

Londres

-1.34

POSITIVE LOGITS

↵

2.09

–

1.55

 already

1.52

 уже

1.48

 know

1.36

to

1.35

することが

1.34

is

1.31

 представляет

1.30

Activations Density 0.061%