INDEX

Explanations

words starting with Sho

The neuron responds whenever it sees the letter sequence “Sho” at the start of a token.

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

是非常

-2.72

-2.53

when

-2.38

 なら

-2.33

there

-2.28

because

-2.27

-2.22

𖡼

-2.20

 でも

-2.19

 あと

-2.17

POSITIVE LOGITS

koszulka

2.58



2.55

2.47

 Перейти

2.44

鹋

2.41

栳

2.38

 geschlagen

2.27

SALES

2.27

 così

2.25

 called

2.23

Activations Density 0.006%