INDEX

Explanations

official titles

This neuron detects uppercase titles and agency or official names (e.g., “ATTORNEY GENERAL,” “CLERK OF COURT,” “DIRECTOR OF CENTRAL INTELLIGENCE”).

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

-1.36

它的

-1.31

人たち

-1.25

 эти

-1.18

 αυτά

-1.17

锉

-1.17

 éstas

-1.16

 которое

-1.16

 они

-1.13

 aquellas

-1.13

POSITIVE LOGITS

 himself

2.14

himself

1.44

who

1.33

 niya

1.29

girlfriend

1.24

════

1.22



1.20

 niyang

1.20

 recommande

1.17

gruß

1.17

Activations Density 0.081%