INDEX

Explanations

a/an followed by importance

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

the

-2.06

二日

-1.76

三月

-1.70

特有

-1.67

 them

-1.65

 from

-1.65

 ONLY

-1.64

 Knowing

-1.63

「

-1.63

antism

-1.63

POSITIVE LOGITS

 also

2.13

</em>

1.98

鸰

1.93

1.80

又不

1.73

なども

1.70

También

1.69

also

1.67

ceptar

1.65

ᡴ

1.64

Activations Density 0.010%