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

çĺ¦

-0.29

miss

-0.28

 miss

-0.25

iences

-0.24

vore

-0.24

 Nord

-0.24

è¿¤

-0.24

èĤ©

-0.23

adores

-0.23

æĲŃ

-0.23

POSITIVE LOGITS

æĺİå¤©

0.27

çıī

0.26

PER

0.26

ï¾Ł

0.25

å®Īä½ı

0.25

æĺİçŁ¥

0.25

ëĭĪëĭ¤

0.24

atsapp

0.24

 VERIFY

0.24

ifie

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.