INDEX

Explanations

references to personal and collective experiences or actions

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

ÑĢÐ°Ð·Ñĥ

-0.07

rophe

-0.07

taire

-0.07

upo

-0.07

à¹Īà¸²à¸Īà¸°

-0.06

ufen

-0.06

áº¥m

-0.06

Ìģt

-0.06

osexual

-0.06

ance

-0.06

POSITIVE LOGITS

ignon

0.06

rys

0.06

are

0.06

ahoma

0.06

unl

0.06

unu

0.06

chas

0.06

alker

0.05

 those

0.05

æŀļ

0.05

Activations Density 0.036%