INDEX

Explanations

source followed by related nouns

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

-1.13

 sliver

-1.13

-1.06

…”

-1.02

<i>

-1.01

 backside

-1.01

-1.00

 sorta

-0.96

اس

-0.96

мой

-0.96

POSITIVE LOGITS

 getSource

1.59

 source

1.48

 источ

1.39

getSource

1.34

 SOURCE

1.32



1.31

ource

1.31

lieu

1.24

—¡

1.24

 sources

1.20

Activations Density 0.056%