INDEX

Explanations

academic programs and fields

The neuron fires on names of academic departments, majors, and professional/educational program titles.

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

 that

-1.54

雋

-1.31

ってない

-1.26

 “(

-1.23

াত

-1.22

-1.20

it

-1.20

 amarilla

-1.13

 madura

-1.12

 简介

-1.12

POSITIVE LOGITS

ARS

1.53

</i>

1.52

we

1.41

 have

1.39

 instead

1.36

୩

1.35



1.34

</em>

1.33

 моя

1.32

 visualización

1.30

Activations Density 0.040%