INDEX

Explanations

cheers and applause

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

úly

-0.88

әне

-0.87

 detalla

-0.82

 prestasi

-0.79

quía

-0.79

recommended

-0.77

反思

-0.75

 outcrops

-0.75

 Васи

-0.73

 recommended

-0.73

POSITIVE LOGITS

 cheers

3.05

 cheered

2.78

 cheering

2.69

 applause

2.53

Cheers

2.17

 cheer

2.16

 Cheers

2.05

 ovation

2.03

cheers

1.99

 appla

1.85

Activations Density 0.030%