INDEX

Explanations

Eugenie, Eugenia names

The neuron fires on occurrences of the character sequence “Eugen” (as in names like Eugene, Eugenia, Evgeny, etc.).

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

 juſt

-2.95

is

-2.77

慊

-2.58

܃

-2.44

:).

-2.38

即便是

-2.31

eniem

-2.31

趿

-2.28

 eſſ

-2.23

炤

-2.23

POSITIVE LOGITS

 понимаю

2.61

 Jenderal

2.31

 Luar

2.30

2.19

putan

2.19

 lenne

2.19

 Budaya

2.17

ጵ

2.16

 berdua

2.16

 الثالث

2.14

Activations Density 0.006%