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

èĩªè´Ł

-0.27

Anc

-0.27

æĦĪ

-0.27

ä¸įè´Ł

-0.25

 Chrysler

-0.25

**

-0.25

 sarc

-0.24

ç½ĳåıĭè¯Ħè®º

-0.24

rega

-0.24

æĦıä¹īä¸Ĭ

-0.24

POSITIVE LOGITS

chet

0.28

KeyUp

0.26

åĮħ

0.25

quina

0.25

è®¤è¯ģ

0.25

Weekly

0.25

çĬ¯

0.24

æĥ³å¿µ

0.23

xu

0.23

/column

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.