INDEX

Explanations

possessive + target audience

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pheric

-0.86

 negoci

-0.83

聚

-0.81

EnableWeb

-0.80

ública

-0.77

Haut

-0.76

 bire

-0.75

aried

-0.73

 morts

-0.73

mely

-0.73

POSITIVE LOGITS

 target

6.19

target

5.03

Target

4.47

 Target

4.41

TARGET

3.78

 audience

3.69

 targeted

3.66

 TARGET

3.42

 targets

3.06

getTarget

3.06

Activations Density 0.077%