INDEX

Explanations

validate

classifying with descriptions and attributes

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

。

0.43

.`

0.40

।

0.39

ämme

0.38

®.

0.37

."

0.37

®

0.36

։

0.36

嬿

0.36

분이

0.35

POSITIVE LOGITS

 certes

0.37

hra

0.36

 overhauled

0.36

&,

0.35

\%,

0.35

'=>'','

0.34

തെന്നും

0.34

captivity

0.33

",[],

0.33

 zwar

0.32

Activations Density 0.123%