INDEX

Explanations

partner or sponsor

The neuron detects mentions of sponsorship or partnership roles and related support terminology.

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

所谓

-1.44

 těch

-1.30

 немає

-1.27

全都

-1.27

 dziś

-1.26

 positivos

-1.24

antemente

-1.23

adori

-1.23

 jaké

-1.20

 případ

-1.17

POSITIVE LOGITS

 both

1.70

the

1.45

of

1.24

 this

1.23

 Both

1.22

чало

1.20

for

1.19

ſ

1.16

</b>

1.16

၂

1.16

Activations Density 0.021%