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

chor

-0.09

ught

-0.08

 camer

-0.08

uries

-0.08

 Laguna

-0.08

 technologies

-0.07

sed

-0.07

Rus

-0.07

essenger

-0.07

uesta

-0.07

POSITIVE LOGITS

)["

0.11

 Mish

0.10

bak

0.10

Zot

0.10

hide

0.09

dec

0.09

 Beth

0.09

Ticker

0.09

 equity

0.09

iros

0.09

Activations Density 0.000%

No Known Activations