INDEX

Explanations

draw

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

InvalidProtocol

-0.92

sizeCache

-0.77

 Normdatei

-0.77

出版年

-0.74

 chofe

-0.69

reportWebVitals

-0.69

 pleaſure

-0.68

 poffe

-0.67

RetentionPolicy

-0.66

Amicalement

-0.65

POSITIVE LOGITS

na

0.42

am

0.40

0.39

nav

0.38

ua

0.37

 alla

0.36

al

0.36

ান

0.36

nal

0.36

烷

0.35

Activations Density 0.053%