INDEX

Explanations

verbs followed by prepositions or adjectives

The neuron fires strongly on content verbs—that is, words denoting actions (in their base or infinitive form).

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

 such

-1.56

 these

-1.45

ebly

-1.45

 those

-1.41

 either

-1.38

-1.33

 other

-1.32

 both

-1.31

 things

-1.31

 STARTED

-1.30

POSITIVE LOGITS

and

1.71

[],

1.55

!,

1.52

~,

1.51

{},

1.49

(),

1.48

"",

1.46

?,

1.44

'',

1.39

”、“

1.39

Activations Density 0.143%