INDEX

Explanations

letter B

The neuron fires on standalone “B” (or “b”) tokens—that is, single‐letter tokens B/b.

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

-1.38

蔓延

-1.24

and

-1.24

-1.23

Â

-1.22

бол

-1.19

by

-1.16

十五

-1.16

 maart

-1.15

ваете

-1.12

POSITIVE LOGITS

another

1.43

 pretože

1.35

 musíte

1.23

 tasas

1.22

 there

1.21

 another

1.20

 другая

1.18

 extremely

1.16

是一個

1.16

 geloof

1.15

Activations Density 0.277%