INDEX

Explanations

suicide and self-destruction

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

 gouden

-1.41

 eenige

-1.35

 ungdom

-1.34

 wciąż

-1.31

ciąg

-1.30

которы

-1.30

 eenig

-1.30

 årets

-1.25

chaussures

-1.23

 bygger

-1.23

POSITIVE LOGITS

for

1.59

gemeester

1.30

 three

1.27

タイム

1.25

two

1.15

ikaze

1.09

 very

1.06

 like

1.06

的表情

1.05

out

1.03

Activations Density 0.034%