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

Kut

-0.08

 Loose

-0.08

 Anderson

-0.08

mec

-0.08

-0.07

 punct

-0.07

 ranging

-0.07

aret

-0.07

-spin

-0.07

 accum

-0.07

POSITIVE LOGITS

 morality

0.13

ethical

0.12

0.11

 resolving

0.11

 moral

0.11

PCS

0.11

 supporting

0.11

 Laur

0.11

 morals

0.11

Ent

0.11

Activations Density 0.000%

No Known Activations