INDEX

Explanations

subjective judgments

The neuron fires on subjective, evaluative adjectives conveying feelings or judgments (e.g. “strange,” “intriguing,” “frustrating,” “obnoxious,” “possible”).

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

 lucru

-1.20

lettre

-1.19

embang

-1.17

 singur

-1.16

 autén

-1.16

 desconocido

-1.15

 merkwür

-1.15

 acesta

-1.15

 nimic

-1.15

 attribué

-1.14

POSITIVE LOGITS

to

3.14

 that

2.00

 because

1.77

for

1.67

 when

1.52

you

1.28

 since

1.20

how

1.17

 these

1.16

 people

1.16

Activations Density 0.052%