INDEX

Explanations

city names and places

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

 باسلام

-1.69

 péché

-1.64

鹇

-1.63

廡

-1.58

Etimología

-1.56

 الاجتماعية

-1.56

 ennen

-1.55

 modelleri

-1.53

 که

-1.53

 قبل

-1.52

POSITIVE LOGITS

 also

2.22

in

2.05

for

2.03

 even

2.03

on

1.98

to

1.97

not

1.63

 however

1.59

 some

1.48

 into

1.41

Activations Density 0.062%