INDEX

Explanations

all those

The neuron consistently activates on the word “All” (especially when it begins a clause).

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

ierungs

-1.25

zeitung

-1.09

atique

-1.09

leggio

-1.09

 bytu

-1.08

πάρχ

-1.04

 chaqueta

-1.02

 några

-1.02

ленность

-1.02

!*\

-1.02

POSITIVE LOGITS

of

3.06

 this

2.20

 these

1.93

you

1.91

 that

1.80

 those

1.59

 they

1.48

it

1.43

 else

1.41

we

1.39

Activations Density 0.032%