INDEX

Explanations

personal experiences and accounts

This neuron activates on mentions of “experience,” i.e. occurrences of the word “experience” in the 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

 more

-1.52

<bos>

-1.50

 should

-1.48

 only

-1.41

 that

-1.38

_{

-1.31

 needs

-1.30

if

-1.28

any

-1.26

 discussion

-1.25

POSITIVE LOGITS

 ſont

1.34

 fonctionnent

1.31

 bré

1.23

 系统

1.23

ppies

1.21

 witte

1.21

 fré

1.20

 zove

1.18

 alho

1.18

куртка

1.17

Activations Density 0.076%