INDEX

Explanations

concepts related to communication and understanding in context

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

utin

-0.07

legen

-0.07

agua

-0.06

ogl

-0.06

acerb

-0.06

_cleanup

-0.06

batim

-0.06

zk

-0.06

ixin

-0.06

ONY

-0.06

POSITIVE LOGITS

 understanding

0.09

 understand

0.09

 understands

0.08

 Armed

0.08

 design

0.07

 decision

0.07

 better

0.07

 later

0.07

 then

0.07

 THEN

0.07

Activations Density 0.033%