INDEX

Explanations

who marked, at the, we will

The neuron fires most strongly on open-class “content” tokens—nouns, verbs, numbers, question marks, and other semantically important words—rather than on common function words.

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

 that

-1.73

 such

-1.52

you

-1.45

and

-1.45

 primarily

-1.43

 mainly

-1.35

 about

-1.32

by

-1.32

 create

-1.30

its

-1.29

POSITIVE LOGITS

𖣔

1.53

 beden

1.42

cách

1.41

pergillus

1.40

hoka

1.37

 accentuated

1.37

rocław

1.36

粜

1.35

ágenes

1.34

೬

1.34

Activations Density 0.125%