INDEX

Explanations

early

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

 >=",

-0.93

rungsseite

-0.91

 kasarigan

-0.85

новништво

-0.77

InjectAttribute

-0.77

AndEndTag

-0.74

URLException

-0.71

richTextPanel

-0.70

 intptr

-0.69

oa̍t

-0.69

POSITIVE LOGITS

 Judaism

0.52

 modernity

0.51

 Jewish

0.51

 Hebrew

0.47

 Zionist

0.44

 anthropological

0.44

Swa

0.44

 curiosity

0.42

minmax

0.42

 communist

0.42

Activations Density 0.006%