INDEX

Explanations

arrays and their properties

The neuron strongly activates on occurrences of the word “array.”

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

↵↵

-2.08

 etwa

-1.80

 \%)$

-1.62

ctivity

-1.59

࿆

-1.57

也都

-1.55

and

-1.52

一方面

-1.52

ina

-1.51

lète

-1.50

POSITIVE LOGITS

 this

1.98

 your

1.64

 sólido

1.50

媖

1.50

これに

1.49

 that

1.44

 FISHING

1.43

けれ

1.41

its

1.41

導致

1.39

Activations Density 0.044%