INDEX

Explanations

first occurrence

The neuron fires on occurrences of the word “first.”

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

you

-2.30

of

-1.98

zegovina

-1.59

同时也

-1.43

 itself

-1.36

发生了

-1.35

 they

-1.34

is

-1.34



-1.34

鸸

-1.33

POSITIVE LOGITS

own

1.94

 besuchen

1.30

 attempt

1.29

صفات

1.27

米国

1.25

 verschiedene

1.23

حص

1.21

 visit

1.16

ちょっと

1.16

Jen

1.14

Activations Density 0.033%