INDEX

Explanations

places and their origin

The neuron is effectively inactive and does not reliably detect any pattern.

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

 ecran

-1.38

𝑵

-1.30

”،

-1.30

 apartament

-1.27

殼

-1.27

泚

-1.27

 pelicula

-1.25

 risico

-1.25

ᜀ

-1.25

jure

-1.24

POSITIVE LOGITS

﨑

1.47

1.45

ряду

1.40

 zehn

1.39

 between

1.38

姥

1.33

'.

1.32

 рассказать

1.31

 Between

1.29

'-

1.28

Activations Density 0.008%