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

rut

-0.09

 selv

-0.08

Dah

-0.08

 haus

-0.08

 reminding

-0.08

 Dahl

-0.08

hoot

-0.08

each

-0.08

clar

-0.08

POSITIVE LOGITS

 Scalars

0.10

prog

0.10

gis

0.10

mare

0.09

 lasted

0.09

 popularity

0.09

zik

0.09

MAND

0.09

bo

0.09

adir

0.09

Activations Density 0.000%

No Known Activations