INDEX

Explanations

references to popular culture, particularly related to beauty and attractiveness

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

enant

-0.07

emoc

-0.07

 homosexuality

-0.07

ibold

-0.07

adius

-0.07

YG

-0.07

innitus

-0.07

_gem

-0.07

chwitz

-0.07

.flush

-0.06

POSITIVE LOGITS

 model

0.11

 models

0.10

 modeling

0.10

 Models

0.09

 modelling

0.09

-model

0.09

 MODEL

0.08

model

0.08

models

0.08

Models

0.08

Activations Density 0.155%