INDEX

Explanations

code punctuation and symbols

opening parentheses in code or mathematical expressions.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

-3.05

↑↑↑</

-2.56

泺

-2.39

-2.38

 forbed

-2.33

 شیپور

-2.19

 timmar

-2.11

 stør

-2.09

 mutta

-2.06

隧

-2.05

POSITIVE LOGITS

 vierten

2.73

妧

2.47

 WHILE

2.34

言语

2.34

жают

2.28

感じた

2.27

we

2.25



2.22

殽

2.20

to

2.17

Activations Density 0.001%