INDEX

Explanations

numerical values and units

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

æ¬¡

-0.07

çķĻåľ¨

-0.06

ima

-0.06

vez

-0.06

 consequential

-0.06

atu

-0.06

åĪĿæģĭ

-0.06

è¿ĩåİ»çļĦ

-0.06

pee

-0.06

Âł

-0.06

POSITIVE LOGITS

éĹ®éĹ®

0.08

anjang

0.08

iteln

0.08

udded

0.08

QUIRE

0.08

isar

0.08

 ninh

0.08

ëł¹

0.07

 Varia

0.07

itored

0.07

Activations Density 0.007%