INDEX

Explanations

driving or riding states

The neuron activates on words that refer to vehicles being driven or used (e.g. “driving,” “driven,” “driver,” “daily driver,” “Sedan”).

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

σκευ

-1.27

énieur

-1.27

mnop

-1.26

 HUGE

-1.20

 создание

-1.19

 Geräten

-1.19

DESCRIPTOR

-1.16

トーン

-1.16

 veiks

-1.16

 bilg

-1.13

POSITIVE LOGITS

 wana

1.38

1.34

 fără

1.27

瑒

1.27

wenn

1.24

:{

1.23

 jouent

1.19

镡

1.18

 températures

1.17

 chon

1.17

Activations Density 0.047%