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

istically

-0.26

ands

-0.26

 meanwhile

-0.26

tails

-0.25

Mob

-0.25

FRING

-0.24

odem

-0.24

 popcorn

-0.24

iros

-0.24

Ð¸ÑĢÑĥ

-0.24

POSITIVE LOGITS

vari

0.26

åħ¬åĳĬ

0.26

relation

0.25

 vari

0.24

difficulty

0.24

ot

0.24

ä¸ªäººä¿¡æģ¯

0.23

ä½ľå¼Ĭ

0.23

 abst

0.23

çĲ°

0.23

Activations Density 0.068%

No Known Activations

This feature has no known activations.