INDEX

Explanations

in the foot

This neuron activates on occurrences of the substring “conan” (in any casing) in identifiers or text.

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

our

-1.66

 搭配

-1.37

 字母

-1.31

 背包

-1.29

 Ее

-1.28

Viernes

-1.23

壓

-1.23

Jawab

-1.22

θεια

-1.19

 seventeen

-1.18

POSITIVE LOGITS

footed

1.48

іан

1.30

 Exactly

1.29

菔

1.26

 parlando

1.24

娅

1.23

gsmål

1.20

vább

1.19

his

1.18

が多い

1.15

Activations Density 0.032%