INDEX

Explanations

listing items connected by and

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



-1.06

 rajut

-1.04

 McCull

-1.03

cumin

-1.03

 disiplin

-1.02

抬手

-1.01

 selam

-1.01

dass

-0.99

 инста

-0.99

nó

-0.98

POSITIVE LOGITS

put

1.37

 make

1.32

get

1.30

 take

1.23

 have

1.23

 subsequently

1.20

 actively

1.19

 immediately

1.17

 become

1.17

 other

1.17

Activations Density 0.197%