INDEX

Explanations

unique identifiers and values

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

↵↵

-2.78

";

-2.22

 mögliche

-1.89

-1.84

to

-1.83

-1.81

 .......

-1.80

 แต่

-1.79

</h3>

-1.77

 pivotal

-1.77

POSITIVE LOGITS

 costuras

2.14

 unrelenting

2.02

just

2.02

 debilitating

2.00

 heartfelt

1.98

There

1.94

鋮

1.86

 gevoel

1.84

 peruano

1.84

 смотреть

1.83

Activations Density 0.010%