INDEX

Explanations

Technical language

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

 nahilalakip

-0.67

 Facts

-0.60

GenerationType

-0.59

endfor

-0.58

План

-0.57

 facts

-0.56

றை

-0.56

+#+

-0.54

 Advocacy

-0.53

esez

-0.53

POSITIVE LOGITS

ContentAsync

0.59

исленность

0.52

noinspection

0.45

vidad

0.43

erover

0.43

TagMode

0.43

ItemBackground

0.42

nee

0.40

utilisons

0.40

 BorderRadius

0.40

Activations Density 0.002%