INDEX

Explanations

in a state or condition

This neuron activates on the prepositions “in” and “into,” especially when they introduce a phrase (e.g. “entry into X,” “in Y”).

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

 wszyscy

-1.47

甚麼

-1.42

 swojej

-1.34

';

-1.33

 wszystkich

-1.33

 wszystkie

-1.32

 всех

-1.29

 himself

-1.29

亿美元

-1.29

耵

-1.28

POSITIVE LOGITS

1.49

</b>

1.45

1.30

by

1.23

由

1.20

an

1.16

one

1.09

humidité

1.06

 andere

1.05

</h1>

1.05

Activations Density 0.093%