INDEX

Explanations

possibility of uncertainty

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

 thánh

-0.88

 idéal

-0.84

デカ

-0.82

 amus

-0.82

 llamar

-0.81

 anglais

-0.80

 ويك

-0.80

jang

-0.80

 Lorsque

-0.79

 skvě

-0.79

POSITIVE LOGITS

 seems

1.21

 evidently

1.16

 apparently

1.15

 seemed

1.03

 Apparently

0.96

 perhaps

0.95

 offenbar

0.94

 presumably

0.93

 probably

0.93

 possibly

0.91

Activations Density 0.058%