INDEX

Explanations

container

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Identification

-2.06

 identification

-2.03

Identification

-1.95

identification

-1.88

 Identi

-1.85

 Identified

-1.83

 identified

-1.81

Identified

-1.78

Identifying

-1.75

 Identifying

-1.74

POSITIVE LOGITS

 Container

1.13

Containers

1.10

 container

1.09

 Containers

1.09

 containers

1.08

Container

1.07

CONTAINER

1.05

container

1.03

 vessels

1.02

容器

0.96

Activations Density 0.086%