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

é²į

-0.28

stor

-0.28

stad

-0.27

Pac

-0.26

çºµæ¨ª

-0.26

å¼Ģå§ĭäºĨ

-0.25

}elseif

-0.25

styl

-0.25

æķŀ

-0.24

dro

-0.24

POSITIVE LOGITS

å¹³è¡Į

0.28

è¿Ļæł·ä¸Ģ

0.26

cestor

0.25

 such

0.25

å¤©çĶŁ

0.24

å¾Ĥ

0.24

èĪ¶

0.23

ceptor

0.23

èĽŃ

0.23

osis

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.