INDEX

Explanations

or followed by options

or explicit or harmful content

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

for

0.45

tio

0.43

and

0.41

For

0.41

aka

0.37

 storyboard

0.37

for

0.36

if

0.36

 bruke

0.34

 δύο

0.34

POSITIVE LOGITS

larda

0.42

л

0.41

naments

0.40

larında

0.40

ల్

0.39

ной

0.38

اً

0.38

Passwords

0.38

sembles

0.38

lardan

0.38

Activations Density 0.693%