INDEX

Explanations

is called

The neuron activates on multi‐word technical term introductions—phrases where something is “called,” “known as,” or “dubbed” (i.e. naming or defining a concept).

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

そんな

-1.30

不同

-1.27

そう

-1.19

-1.18

那么

-1.17

 deth

-1.17

 один

-1.17

Выводы

-1.17

となると

-1.16

 kidna

-1.15

POSITIVE LOGITS

 because

1.53

蟊

1.51

 they

1.51

cable

1.46

for

1.46

but

1.45

€”

1.35

有任何

1.34

we

1.32

 today

1.32

Activations Density 0.093%