INDEX

Explanations

attract customers

This neuron fires on numeric tokens (i.e. sequences of digits or numbers) rather than ordinary words.

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

if

-1.38

of

-1.32

もし

-1.29

 égard

-1.21

 according

-1.20

 純正

-1.20

︲

-1.17

Тарих

-1.15

ishw

-1.14

 dise

-1.13

POSITIVE LOGITS

 plötzlich

1.30

 großen

1.25

彼らは

1.20

瑧

1.12

 avanza

1.12

 große

1.09

着的

1.09

 dostępne

1.05

 návr

1.05

ᛟ

1.05

Activations Density 0.083%