INDEX

Explanations

being aware or sure

The neuron fires on occurrences of the word “sure,” especially in the phrase “make sure.”

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

してる

-1.45

佣

-1.39

 algún

-1.39

-1.22

メージ

-1.20

 algunos

-1.19

 List

-1.18

="",

-1.17

xions

-1.16

]+\

-1.16

POSITIVE LOGITS

 liknande

1.59

même

1.54

 iſt

1.41

 szczeg

1.38

ቼ

1.36

 тоже

1.35

 Även

1.34

اين

1.33

 directiva

1.33

 plegable

1.30

Activations Density 0.033%