INDEX

Explanations

apology, ultimatum, extend, alibi, excuse

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

 Announced

-0.85

Enlight

-0.85

 Announcements

-0.84

anap

-0.83

Noice

-0.75

peny

-0.75

anonym

-0.75

Doo

-0.73

 kirim

-0.73

ወ

-0.73

POSITIVE LOGITS

an

1.77

Ul

1.47

 ultimatum

1.30

ulti

1.18

Ul

1.16

 ulti

1.09

 olive

0.98

uli

0.90

 apology

0.88

HandleFunc

0.87

Activations Density 0.052%