INDEX

Explanations

as a or an

The neuron detects “as a” (and “as an”) constructions introducing a role or capacity.

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

 they

-1.60

 that

-1.37

aliers

-1.27

 make

-1.20

if

-1.19

Tradu

-1.19

 take

-1.16

了一些

-1.15

for

-1.14

多少钱

-1.13

POSITIVE LOGITS

2.39

AGEMENT

1.34

an

1.29

 anúncio

1.29

 acidente

1.27

 pacote

1.26

 növény

1.25

 både

1.20

 aparelho

1.17

 xadrez

1.16

Activations Density 0.050%