INDEX

Explanations

moving around

The neuron strongly responds to occurrences of the preposition “around,” i.e. phrases indicating movement or spatial relation using “around.”

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

 rafra

-1.70

re

-1.68

 that

-1.68

 cuida

-1.66

何度も

-1.62

仅仅

-1.59

 любой

-1.54

-1.52

 bientôt

-1.52

 comienza

-1.52

POSITIVE LOGITS

in

1.83

for

1.57

޸

1.55

 список

1.53

 количество

1.52

 включая

1.50

 elevating

1.48

好用

1.48

 život

1.47

МЕ

1.46

Activations Density 0.013%