INDEX

Explanations

you to

The neuron strongly activates on occurrences of the second‐person pronoun “you” (and similarly short direct‐address or function words).

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

my

-1.32

 veränder

-1.27

chehen

-1.27

 policiales

-1.25

hilterra

-1.23

ersk

-1.22

fty

-1.22

-1.19

ógicas

-1.19

it

-1.18

POSITIVE LOGITS

る

1.20

gefunden

1.16

 بعض

1.15

房

1.13

sel

1.13

styleUrls

1.12

for

1.10

尤

1.10

וה

1.08

Activations Density 0.051%