INDEX

Explanations

references to scientific concepts and structures in the context of physical laws and equations

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

 mass

-0.07

ONO

-0.06

 conc

-0.06

sed

-0.06

_ASSOC

-0.06

 argent

-0.06

 manner

-0.06

alore

-0.06

ł

-0.05

POSITIVE LOGITS

uttle

0.06

ultz

0.06

Ľå»º

0.06

nar

0.06

Literal

0.06

 misd

0.06

cket

0.06

egot

0.06

yer

0.06

standing

0.06

Activations Density 0.004%