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

 conj

-0.10

iani

-0.09

 Bris

-0.09

 Savage

-0.09

 Rotary

-0.08

dn

-0.08

 Griff

-0.08

gent

-0.08

 bump

-0.08

tas

-0.08

POSITIVE LOGITS

 futures

0.11

 careers

0.11

 assim

0.10

 Proto

0.10

 themselves

0.10

ISON

0.10

ottie

0.10

lu

0.10

 Harding

0.10

proto

0.09

Activations Density 0.000%

No Known Activations