INDEX

Explanations

mentions of the specific chemical poisons

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

 myſelf

-0.72

 виправивши

-0.70

 itſelf

-0.70

 himſelf

-0.62

Efq

-0.61

 Dernière

-0.60

 reaſon

-0.60

 muri

-0.59

 uncin

-0.58

 mView

-0.57

POSITIVE LOGITS

 pois

3.11

 Pois

2.05

 pues

1.78

pois

1.75

Pois

1.42

 porque

1.23

 poiché

1.14

 pero

1.13

 hiszen

1.12

 Pues

1.10

Activations Density 0.005%