INDEX

Explanations

phrases and concepts related to legal and moral obligations

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

 tavs

-0.07

 ActiveForm

-0.07

Ð¾ÑĢÐ¾ÑĤ

-0.07

plemented

-0.07

Ø®Øµ

-0.06

valuator

-0.06

Anywhere

-0.06

à¸Ńà¸³

-0.06

å¯¶

-0.06

ÑĢÐ°Ð±

-0.06

POSITIVE LOGITS

 owed

0.17

 towards

0.15

 toward

0.14

 incumbent

0.13

 imposed

0.12

 Towards

0.11

 obligation

0.10

Ow

0.10

 obligations

0.10

owe

0.10

Activations Density 0.025%