INDEX

Explanations

references to prior actions or events described in a timeline

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

ÙģØ´

-0.07

old

-0.07

ris

-0.07

Ø©

-0.07

stan

-0.07

aud

-0.07

ening

-0.07

au

-0.07

eres

-0.07

urg

-0.06

POSITIVE LOGITS

 being

0.12

/post

0.09

 Being

0.07

Being

0.07

being

0.07

 publication

0.07

 actual

0.07

Å¼e

0.07

usra

0.07

/at

0.06

Activations Density 0.012%