INDEX

Explanations

populist and establishment politics, Warren

This neuron detects occurrences of “popul” strings—i.e. words like populist or populism indicating populist political language.

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

to

-1.41

 Typically

-1.38

coeur

-1.34

so

-1.32

cota

-1.30

 هاي

-1.30

ustomed

-1.29

}-{

-1.28

 Obviously

-1.27

 Moreover

-1.27

POSITIVE LOGITS

↵↵

1.66

 mindig

1.48

 chevaux

1.30

 italiens

1.23

 attaques

1.22

 pierres

1.20

のおかげ

1.20

 épreuves

1.18

 circonstances

1.17

螃

1.17

Activations Density 0.034%