INDEX

Explanations

special characters or symbols that may indicate specific linguistic or cultural elements

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ï¿½

-0.06

 ïĤ

-0.06

ï

-0.06

ÂĿ

-0.06

à¥įà¤ªà¤¤

-0.06

 undercover

-0.06

 Beckham

-0.06

KD

-0.06

ïĢ

-0.06

=http

-0.06

POSITIVE LOGITS

 fucking

0.14

 fuck

0.13

 fucks

0.13

 FUCK

0.13

Fuck

0.13

 Fucking

0.12

 fucked

0.12

fuck

0.12

 shitty

0.12

 Fuck

0.12

Activations Density 0.003%