INDEX

Explanations

plot axis ticks and labels

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

 sentire

-0.72

PAIGN

-0.71

yttö

-0.70

色の

-0.69

Totale

-0.69

zám

-0.69

Cef

-0.69

 tradic

-0.68

 طلب

-0.68

 появится

-0.67

POSITIVE LOGITS

 labels

1.46

rotation

1.45

 tick

1.41

labels

1.38

 rotation

1.26

xticks

1.25

Labels

1.25

 ticks

1.20

ticks

1.19

tick

1.16

Activations Density 0.016%