INDEX

Explanations

words or phrases that introduce lists or groups of things

I am unable to determine a pattern. The top positive logits do not have a clear trend

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

 pinulongan

-0.82

GenerationType

-0.73

XmlAccessType

-0.67

 Italijanski

-0.64

 дописавши

-0.64

 transférez

-0.62

']);

-0.61

 محفوظة

-0.61

IMPORTED

-0.59

Aiheesta

-0.59

POSITIVE LOGITS

matitis

0.55

 päät

0.52

ERIES

0.51

setRequest

0.51

 warga

0.51

 tartalomajánló

0.49

estris

0.49

 puissiez

0.48

abus

0.47

beiten

0.47

Activations Density 1.753%