INDEX

Explanations

acting for or by someone's authority

The neuron fires on abstract, conceptual nouns (especially nominalizations like discretion, interpretation, disposal, etc.).

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

you

-1.66

for

-1.38

łaś

-1.34

 einwand

-1.32

 moeite

-1.27

 ftate

-1.26

 sfeer

-1.26

 eenvoudig

-1.25

 bijzondere

-1.25

 uitzicht

-1.24

POSITIVE LOGITS

DESCRIPCIÓN

1.52

oooo

1.42

。

1.38

Our

1.37

</h2>

1.35

</h1>

1.34

 fera

1.33

۴

1.32

 ultimi

1.31

࿚

1.31

Activations Density 0.036%