INDEX

Explanations

bund with specific suffixes

The neuron fires on any token containing the substring “bund” (e.g. bundler, bundling, bundled, Bund).

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

месте

-2.55

нутрен

-2.36

нутри

-2.36

鰲

-2.31

 Hinblick

-2.23

蛧

-2.22

 speziellen

-2.19

这里

-2.19

стреча

-2.14

полне

-2.11

POSITIVE LOGITS

ers

2.92

2.88

吓得

2.48

捽

2.47

抠

2.47

</b>

2.39



2.34

 firſt

2.25

硨

2.25

狆

2.23

Activations Density 0.005%