INDEX

Explanations

recognized as

The neuron fires strongly on copular/passive verb constructions centered around “be” (e.g. “to be,” “proven to be,” “shown to be,” “recognized as”).

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

ější

-1.54

Pemer

-1.44

踌

-1.39

ymmetric

-1.32

 ͡°

-1.30

getMock

-1.28

粼

-1.27

LikeLiked

-1.26

 dizaine

-1.25

omic

-1.24

POSITIVE LOGITS

↵

1.77

 ubiquitous

1.41

PARATUS

1.38

 srebr

1.35

 instalada

1.34

}$,

1.34

 disegno

1.33

얻

1.33

と共に

1.33

 Unterschiede

1.32

Activations Density 0.037%