INDEX

Explanations

about me

The neuron strongly activates on the word “about.”

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ر

1.59

льній

1.28

ه

1.25

SCE

1.22

ྜ

1.21

льну

1.20

एस

1.16

هي

1.16

দে

1.14

CAL

1.13

POSITIVE LOGITS

راہیم

1.52

ள்ளது

1.51

iniai

1.46

いた

1.45

ಲ್ಲಿ

1.44

et

1.40

 hinaus

1.38

mäß

1.34

inence

1.33

inė

1.33

Activations Density 0.167%