INDEX

Explanations

phrases and concepts related to statistical increases and trends

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

srv

-0.08

lom

-0.07

avic

-0.07

 éĢģ

-0.07

oust

-0.07

celik

-0.07

avier

-0.07

roe

-0.07

aveled

-0.07

andon

-0.06

POSITIVE LOGITS

 unders

0.07

 fall

0.07

 Fall

0.07

0.06

ely

0.06

Fall

0.06

le

0.06

?url

0.06

 ration

0.06

unders

0.06

Activations Density 0.018%