INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imir

-0.09

lle

-0.09

nier

-0.09

 summit

-0.08

leigh

-0.08

osta

-0.08

Pak

-0.08

 mural

-0.07

 indications

-0.07

 Visible

-0.07

POSITIVE LOGITS

rag

0.11

phant

0.10

pha

0.10

Nik

0.10

Nin

0.10

edia

0.10

 Tanner

0.10

gence

0.10

Mode

0.09

Activations Density 0.000%

No Known Activations