INDEX

Explanations

The International

This neuron detects sentence-initial tokens (words appearing at the start of sentences, which are capitalized).

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

ⓒ

-1.34

餽

-1.32

ımı

-1.30

Flickr

-1.30

 チラシ

-1.30

?”

-1.27

ificado

-1.26

or

-1.26

chenta

-1.26

')

-1.25

POSITIVE LOGITS

 VERY

1.64

 have

1.57

 REALLY

1.50

 โดย

1.50

 jeden

1.45

The

1.41

 fünf

1.41

 coloca

1.37

 alcune

1.34

1.30

Activations Density 0.004%