INDEX

Explanations

No Explanations Found

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

.ul

-0.25

arium

-0.25

arm

-0.25

å§¨

-0.23

ä¸½

-0.23

 scrapped

-0.23

avers

-0.23

äººæł¼

-0.23

 Armour

-0.23

-arm

-0.23

POSITIVE LOGITS

 Lives

0.25

Segue

0.24

 onBind

0.23

ä¸įå¿ĺ

0.23

','',

0.22

é«ĺæĸ°

0.22

olia

0.22

Č↵

0.22

è¯Ń

0.22

turnstile

0.22

Activations Density 0.001%

No Known Activations

This feature has no known activations.