INDEX

Explanations

what follows questions

The neuron activates on interrogative lead-in phrases at the start of a question—especially “In what…,” “To what…,” “what,” or similar question-opening constructs.

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

媖

-1.27

 laku

-1.24

 takiej

-1.23

 ͡°

-1.21

 chyb

-1.20

 trânsito

-1.17

maquina

-1.14

 wersji

-1.13

见状

-1.13

͡

-1.12

POSITIVE LOGITS

An

1.27

or

1.24

Are

1.21

And

1.15

 Once

1.12

1.11

 While

1.11

1.10

 مرة

1.10

на

1.10

Activations Density 0.018%