INDEX

Explanations

pejorative or mocking references to unflattering office behaviors or personalities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vice

-0.53

ору

-0.49

çu

-0.48

Ple

-0.48

 Vice

-0.47

 oprot

-0.44

iprot

-0.44

inescence

-0.43

\,\

-0.43

 stab

-0.42

POSITIVE LOGITS

 boss

3.11

boss

2.66

 Boss

2.66

Boss

2.56

 bosses

2.38

 BOSS

2.09

BOSS

1.77

ボス

1.13

 chefe

1.13

 jefe

1.10

Activations Density 0.002%