INDEX

Explanations

phrases related to records or record-setting events

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

burgh

-0.07

 Jarvis

-0.07

aves

-0.06

ust

-0.06

igo

-0.06

age

-0.06

elman

-0.06

erator

-0.05

isan

-0.05

POSITIVE LOGITS

-breaking

0.15

-setting

0.12

breaking

0.12

-level

0.11

 levels

0.11

-high

0.10

ingly

0.10

number

0.10

 breaking

0.10

 number

0.10

Activations Density 0.006%