INDEX

Explanations

text segment beginnings

The neuron activates specifically on the standalone token “The,” i.e. the definite article “The.”

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

 What

-1.30

by

-1.29

&#

-1.23

 menyediakan

-1.21

 Excellent

-1.20

-1.18

its

-1.09

Did

-1.09

at

-1.07

for

-1.06

POSITIVE LOGITS

鐽

1.50

饜

1.40

 grossa

1.33

︕

1.22

 mauva

1.21

⾞

1.20

𓐍

1.20

 adesi

1.19

 maniere

1.17

￬

1.17

Activations Density 0.000%