INDEX

Explanations

increase and balance

The neuron fires on nouns that name personal attributes or abilities presented as benefits or improvements (e.g. esteem, interpersonal skills, balance).

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

to

-2.50

the

-2.00

it

-1.49

几分

-1.45

 Then

-1.43

for

-1.43

脚步

-1.43

 them

-1.41

完成です

-1.39

 their

-1.37

POSITIVE LOGITS

。”

1.59

鹇

1.44

ERTY

1.44

自分が

1.43

1.42

婞

1.40

jewództ

1.38

and

1.38

 protože

1.37

ERSHIP

1.37

Activations Density 0.112%