INDEX

Explanations

vampire and vampires

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

 despo

-0.79

 cáncer

-0.79

 Wachs

-0.77

 skimage

-0.77

 Fische

-0.77

 shaman

-0.75

 Aladdin

-0.73

궈

-0.73

 buddha

-0.72

nium

-0.70

POSITIVE LOGITS

 vampire

3.44

 vampires

3.14

 Vampire

2.72

 vamp

2.61

 Vamp

2.41

 Dracula

2.34

vampire

2.27

吸血

2.27

Vamp

2.23

Vampire

2.17

Activations Density 0.035%