INDEX

Explanations

murder and deaths of families

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

 Collision

-0.77

lerde

-0.73

ella

-0.72

 нале

-0.71

 regions

-0.71

色

-0.71

Joystick

-0.71

囚

-0.70

verti

-0.69

 cohorts

-0.69

POSITIVE LOGITS

 family

1.14

murder

1.12

 murder

1.09

 throats

1.05

 murders

1.03

 massac

0.99

 massacre

0.98

 execution

0.97

 famili

0.96

family

0.94

Activations Density 0.034%