INDEX

Explanations

column and table data tags

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

 thought

-1.38

 thinking

-1.22

 think

-0.89

 Američ

-0.83

 pensiero

-0.82

 Thought

-0.81

 contemplating

-0.79

 pensamiento

-0.77

親切

-0.76

thought

-0.74

POSITIVE LOGITS

col

1.10

col

1.05

Kol

1.02

Col

1.02

 Gogh

0.98

kol

0.97

Kol

0.94

Col

0.89

 colonized

0.88

addColumn

0.87

Activations Density 0.004%