INDEX

Explanations

mountain peaks and geography

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

 landslide

-0.91

 downhill

-0.87

 altitude

-0.84

山上

-0.82

 altitud

-0.81

 mountain

-0.79

 Alps

-0.78

 mountainous

-0.76

ButtonText

-0.75

 Felsen

-0.75

POSITIVE LOGITS

 daun

0.77

 hende

0.76

 peaks

0.76

Lang

0.75

пі

0.71

 addiction

0.69

 الواقع

0.68

HOE

0.67

 Wilmington

0.67

 Tris

0.67

Activations Density 0.024%