INDEX

Explanations

David followed by surname

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 prejudice

-0.10

 breakout

-0.09

isa

-0.09

 breaking

-0.08

åĲįç§°

-0.08

ëĿ¼

-0.08

 miejs

-0.08

otta

-0.07

 entr

-0.07

POSITIVE LOGITS

owitz

0.14

sonian

0.12

off

0.12

son

0.12

.TextUtils

0.12

sons

0.11

 Rockefeller

0.11

Aws

0.11

 prow

0.11

ovich

0.11

Activations Density 0.063%