INDEX

Explanations

references to characters and narratives in animated films

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Auschwitz

-0.08

Wer

-0.07

ãĥ³ãĤ¬

-0.07

afx

-0.07

èį

-0.07

auge

-0.07

 grey

-0.06

 ÑĨÐµÑĢÐºÐ¾Ð²

-0.06

à¸¶à¸ģ

-0.06

 Fukushima

-0.06

POSITIVE LOGITS

 Prince

0.10

addin

0.10

 prince

0.09

 Desert

0.09

Prince

0.09

 princes

0.09

 Princess

0.08

 genie

0.08

 princess

0.08

 Arabian

0.08

Activations Density 0.003%