INDEX

Explanations

simply put

The neuron detects stock “put simply”–style introductory phrases (e.g. “Simply put,” “Put plainly,” etc.) used to signal a concise restatement.

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

-1.52

SLOT

-1.48

:{

-1.42

 ausdrücklich

-1.42

Might

-1.41

eddable

-1.38

 solch

-1.34

}>;

-1.34

poň

-1.34

ą

-1.31

POSITIVE LOGITS

why

1.55

1.53

 alebo

1.44

 хотели

1.43

ホームページ

1.42

1.38

 dinosaurio

1.38

how

1.37

poleon

1.32

 použí

1.30

Activations Density 0.012%