INDEX

Explanations

quantifiers

This neuron activates on numeric tokens or quantifiers—i.e. numbers (including multi-digit, decimal, or spelled-out counts) in the text.

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

desain

-1.20

FFA

-1.20

palla

-1.17

buen

-1.16

ACZ

-1.14

雷霆

-1.11

 poitrine

-1.09

waist

-1.09

EEN

-1.09

CEE

-1.08

POSITIVE LOGITS

没有

1.45

 hôtel

1.33

不需要

1.22

不是

1.20

 ersche

1.16

 YellowPages

1.12

沒有

1.11

or

1.11

 utilizz

1.10

بيرة

1.10

Activations Density 0.166%