INDEX

Explanations

note, error, clarify, another

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Âł

-0.08

impl

-0.07

 impl

-0.07

par

-0.07

urn

-0.06

è¿Ļå°±

-0.06

quier

-0.06

sequent

-0.06

ouv

-0.06

inary

-0.06

POSITIVE LOGITS

æ±Ĥäºº

0.08

arder

0.07

rej

0.07

ãĥĢãĥ«

0.07

è¿Łå»¶

0.07

æĪĲåĳĺåįķä½į

0.07

gris

0.07

æļ§

0.07

amid

0.07

å»¶

0.07

Activations Density 0.037%