INDEX

Explanations

position within a group

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

 včetně

-1.99

 Anſ

-1.83



-1.78

 egyik

-1.77

𓍊

-1.72

 για

-1.70

AdvEx

-1.65

 パッド

-1.64

骸

-1.64

 essenciais

-1.63

POSITIVE LOGITS

of

2.06

1.92

ers

1.91

1.88

who

1.84

after

1.84

 compel

1.77

1.73

if

1.72

our

1.70

Activations Density 0.016%