INDEX

Explanations

number of

The neuron activates on words or phrases that express quantities or amounts—e.g. quantifiers like “many of the,” “most of the,” “a number of,” “a few,” and “some.”

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

for

-1.55

see

-1.23

そして

-1.22

着用

-1.16

 disposition

-1.16

 neither

-1.14

 demonstration

-1.14

 получает

-1.12

 technique

-1.12

然後

-1.11

POSITIVE LOGITS

 måned

1.23

 alltid

1.22

 omkring

1.21

 befolk

1.20

 habrían

1.18

 området

1.15

 trå

1.13

 murieron

1.13

きましょう

1.13

 from

1.13

Activations Density 0.139%