INDEX

Explanations

is said to

The neuron fires on occurrences of the speech‐act verb “say” (e.g. “said,” “say,” “is said to,” “can be said to,” etc.).

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

 Zähne

-1.44

᭝

-1.41

にほんブログ村

-1.40



-1.39

 svoju

-1.34

 another

-1.33

 obrazov

-1.33

เล็ก

-1.32

giày

-1.32

 issues

-1.32

POSITIVE LOGITS

“

1.81

1.47

``

1.44

『

1.43

we

1.40

 künftig

1.38

 MANY

1.34

「

1.33

 nachdem

1.32

1.31

Activations Density 0.025%