INDEX

Explanations

CPS question data based

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

 what

-1.53

 huge

-1.34

"}";

-1.32

 even

-1.31

%)$

-1.28

 τοῦ

-1.28

 گیاه

-1.25

 initiating

-1.24

 میوه

-1.23

mainPanel

-1.23

POSITIVE LOGITS

Kenmerken

1.77

וּ

1.74

 JOSÉ

1.55

 RECOMM

1.50

 Vitamina

1.47

 бампер

1.46

暧

1.46

Soorten

1.46

ִּ

1.45

 saveurs

1.45

Activations Density 0.026%