INDEX

Explanations

ex vivo study

The neuron activates on words beginning with the prefix “dis.”

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

 another

-1.30

 desbloquear

-1.30

 ajustado

-1.29

 encantador

-1.28

ではまた

-1.27

ではでは

-1.26

the

-1.23

这件事情

-1.16

此事

-1.16

 dedication

-1.14

POSITIVE LOGITS

メリカ

1.25

ates

1.19

Более

1.17

Теперь

1.17

 sosi

1.14

Среди

1.13

Также

1.12

1.11

Activations Density 0.036%