INDEX

Explanations

hashtag components

The neuron detects named entities and hashtags—that is, capitalized brand/event names and “#” tags.

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

it

-1.45

as

-1.41

and

-1.37

 without

-1.33

 with

-1.23

for

-1.14

an

-1.13

two

-1.13

 three

-1.11

Two

-1.09

POSITIVE LOGITS

1.69

/#

1.58

,#

1.55

 hashtag

1.51

たぶん

1.42

顚

1.39

だいたい

1.39

 diriger

1.34

">#

1.30

 savag

1.29

Activations Density 0.012%