INDEX

Explanations

phrases expressing adequacy or sufficiency

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

atak

-0.08

abra

-0.08

aldo

-0.07

arium

-0.07

 rather

-0.07

itter

-0.06

 none

-0.06

Ãºa

-0.06

edo

-0.06

kir

-0.06

POSITIVE LOGITS

 merely

0.15

 simply

0.13

 mere

0.13

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.12

 simplement

0.12

mere

0.10

ë§Į

0.09

 Simply

0.09

Simply

0.08

ä»ħ

0.08

Activations Density 0.004%