INDEX

Explanations

the word "Marine"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Παραπομπές

-0.87

 Thackeray

-0.86

 Yugos

-0.83

出版年

-0.83

 Agamemnon

-0.83

 Anſ

-0.79

োগ

-0.78

DockStyle

-0.77

aç

-0.74

AUC

-0.72

POSITIVE LOGITS

 Marine

1.23

 MARINE

1.19

 marine

1.14

Marine

1.14

 marines

1.05

 Marines

1.01

marine

0.88

 Marin

0.86

marines

0.83

Marin

0.80

Activations Density 0.003%