INDEX

Explanations

lots of / many

The neuron fires on vague quantity words (e.g. “lots,” “lot,” “few”).

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

 today

-1.76

 včetně

-1.63

of

-1.63

including

-1.50

 that

-1.43

 against

-1.41

—

-1.39

نی

-1.35

for

-1.32

 木製

-1.30

POSITIVE LOGITS

(>

1.57

⑉

1.47

大量的

1.46

illante

1.41

 dejaron

1.40

 plásticos

1.34

二日

1.33

唯一的

1.33

 puedes

1.32

これに

1.31

Activations Density 0.052%