INDEX

Explanations

this reference or variable

The neuron flags occurrences of the pronoun “this” (i.e. references to “this” in text or code).

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

 také

-1.46

 also

-1.30

 winner

-1.29

 university

-1.27

次

-1.23

 Bewertungen

-1.21

 singer

-1.20

 auch

-1.20

levance

-1.20

疹

-1.19

POSITIVE LOGITS

 only

1.28

もしくは

1.23

こんばんは

1.17

 ‘‘

1.16

 discernible

1.14

$/$

1.14

 groupings

1.13

 minimalistic

1.13

 multitudes

1.12

‘‘

1.10

Activations Density 0.066%