INDEX

Explanations

and or conjunctions after commas

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

 though

-1.49

 which

-1.45

 however

-1.42

 although

-1.34

but

-1.32

 both

-1.30

 either

-1.16

so

-1.16

 usually

-1.14

たとえば

-1.13

POSITIVE LOGITS

and

2.23

 .......

1.20

............

1.19

 ........

1.14

 .............

1.13

 ..........

1.13

 sieben

1.13

...!

1.12

 .........

1.12

etc

1.12

Activations Density 0.082%