INDEX

Explanations

references to weather-related disruptions or emergencies

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

weeks

-0.07

 Months

-0.07

Months

-0.07

months

-0.07

 months

-0.07

 month

-0.07

_months

-0.07

 Month

-0.06

 decom

-0.06

äºĶæľĪ

-0.06

POSITIVE LOGITS

 weather

0.11

/weather

0.10

 snow

0.09

weather

0.09

 cancell

0.09

 Weather

0.09

Weather

0.09

 morning

0.08

decision

0.08

snow

0.08

Activations Density 0.002%