INDEX

Explanations

tracking property status

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

𝒕

2.82

𝒊

2.80

wati

2.77

عرِّف

2.72

oze

2.54

”).

2.50

zości

2.49

جھ

2.46

”，“

2.45

cated

2.40

POSITIVE LOGITS

▻

2.21

uda

2.12

หนัก

2.06

пети

2.04

1.98

linear

1.97

ەك

1.96

 report

1.95

round

1.91

middot

1.89

Activations Density 0.355%