INDEX

Explanations

it was

This neuron responds to occurrences of the pronoun “it.”

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

なお

-1.20

 なお

-1.08

ユーザ

-1.08

 bucal

-1.08

agora

-1.05

ина

-1.02

RESUMO

-1.02

ствии

-1.02

的笑容

-1.02

Ahora

-1.02

POSITIVE LOGITS

1.55

Kenapa

1.33

 different

1.29

 väldigt

1.24

 like

1.23

Kelebihan

1.20

 there

1.17

 mutta

1.13

Bukan

1.13

Kondisi

1.12

Activations Density 0.008%