INDEX

Explanations

out of

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

and

-0.91

Lê

-0.79

OCTOBER

-0.78

hringer

-0.77

Mobil

-0.75

 Disco

-0.74

 коды

-0.73

 комиссии

-0.73

YO

-0.72

Према

-0.70

POSITIVE LOGITS

of

1.80

 feiert

0.88

 '.')

0.85

 Investigación

0.84

ivin

0.84

 this

0.82

 menyenangkan

0.81

 Ciencias

0.81

 Protects

0.81

 ?></

0.80

Activations Density 0.015%