INDEX

Explanations

code identifiers and paths

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

 sachsen

-0.93

 lachen

-0.91

 klarer

-0.90

 oignons

-0.89

 trattano

-0.88

為に

-0.86

を選択します

-0.86

 koste

-0.85

 heilig

-0.84

Obr

-0.84

POSITIVE LOGITS

 other

1.20

tosí

0.96

all

0.93

drawSprites

0.90

 попере

0.86

التالي

0.84

 tillbaka

0.84

ívar

0.84

 this

0.82

 miners

0.81

Activations Density 0.001%