INDEX

Explanations

robustness and durability

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

轤

-1.02

ління

-0.98

 namorado

-0.96

Demografia

-0.94

 eſſ

-0.93

今も

-0.92

 seno

-0.92

 Isto

-0.91

 jeopardi

-0.91

UALLY

-0.91

POSITIVE LOGITS

 against

1.48

yet

1.40

 enough

1.28

 robust

1.25

and

1.23

yet

1.18

 robustness

1.14

 durability

1.12

 construction

1.09

but

1.07

Activations Density 0.031%