INDEX

Explanations

place to

This neuron detects words that describe an inviting location or setting (e.g. “place,” “environment,” “where”) offering a safe space or venue for people to come and do something.

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

-1.73

-1.61

 sorprende

-1.51

-1.42

What

-1.40

it

-1.36

its

-1.29

use

-1.28

 Übung

-1.28

-1.26

POSITIVE LOGITS

for

1.64

ciale

1.44

to

1.44

ourcen

1.37

 той

1.34

nadores

1.34

)))),

1.31

 радио

1.31

ógicos

1.29

ciaal

1.28

Activations Density 0.054%