INDEX

Explanations

quoted speech starting with specific words

The neuron is mainly triggered by non-alphabetic tokens—things like quotation marks, numbers, and other punctuation.

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

of

-1.89

as

-1.48

-1.44

-1.37

-1.35

珎

-1.32

on

-1.29

呖

-1.28

()

-1.27

putnik

-1.27

POSITIVE LOGITS

 volverá

1.48

迨

1.42

 comenzará

1.41

 échanti

1.38

 Púb

1.32

 Ucrania

1.29

 fecond

1.26

ñores

1.26

秋冬

1.24

 urbanas

1.24

Activations Density 0.004%