INDEX

Explanations

references to harmful substances or 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

principalTable

-0.69

writerow

-0.60

NameInMap

-0.57

setVerticalGroup

-0.56

RTCK

-0.55

AxisAlignment

-0.54

empat

-0.54

 unimp

-0.52

();)

-0.52

onucleotide

-0.51

POSITIVE LOGITS

 harmful

2.41

 Harmful

2.02

Harmful

1.67

 injurious

1.12

harm

0.86

有害

0.77

SPECIFIED

0.68

rrggbb

0.68

évaluateur

0.68

 gustan

0.65

Activations Density 0.001%