INDEX

Explanations

exact explanation or sentence

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 있던

1.64

불어

1.62

 각각

1.60

 cock

1.46

 sempat

1.45

ணா

1.44

 있는지

1.44

utig

1.42

ளிர்

1.42

뎅

1.41

POSITIVE LOGITS

्ह

2.11

widehat

2.02

ية

1.96

電流

1.89

tarea

1.84

ะ

1.77

 اتارنا

1.77

íta

1.76

 प्रमाण

1.75

puts

1.75

Activations Density 0.000%