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

Ð²Ðµ

-0.26

Them

-0.25

 waiver

-0.25

 Markus

-0.25

orrent

-0.24

æ³Ĺ

-0.24

çķľ

-0.24

\/\/

-0.24

 oppos

-0.24

çķ¢

-0.23

POSITIVE LOGITS

çłĶç©¶äººåĳĺ

0.26

.spark

0.26

è´£ä»»åĪ¶

0.25

.Variable

0.25

ä¹ĺ

0.24

è´£ä»»

0.24

ãģ¨ãĤĤ

0.23

etrize

0.23

acky

0.23

CONN

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.