INDEX

Explanations

references to potentially harmful or damaging effects

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

WritableDatabase

-0.68

zinho

-0.63

ulador

-0.62

Datuak

-0.60

ocyan

-0.58

migrationBuilder

-0.57

addContainerGap

-0.57

PLW

-0.56

TTS

-0.54

 bâton

-0.54

POSITIVE LOGITS

 injuring

1.18

 harming

1.10

 impair

1.09

 endangering

1.05

 ruining

1.00

 damaging

0.96

 offending

0.96

 disrupting

0.95

 destroying

0.94

 infecting

0.92

Activations Density 0.032%