INDEX

Explanations

in construction or design

The neuron selectively activates on descriptive adjectives (qualities or properties) in the text.

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

 which

-1.67

 from

-1.43

 Если

-1.23

of

-1.18

 которые

-1.16

by

-1.10

 Pflichten

-1.06

 during

-1.05

for

-1.01

も

-1.01

POSITIVE LOGITS

 Juegos

1.29

=="

1.22

 alça

1.20

éndose

1.17

 maniere

1.13

aş

1.10

の作成

1.09

 agencia

1.09

зовые

1.07

 frança

1.06

Activations Density 0.071%