INDEX

Explanations

compound noun phrases

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

 только

-1.23

 skrev

-1.17

leggio

-1.13

ɝ

-1.09

 بيها

-1.08

 уже

-1.07

 décennies

-1.07

if

-1.07

 если

-1.05

 можно

-1.04

POSITIVE LOGITS

 their

1.44

 have

1.34

 contemporary

1.16

 these

1.16

ுக

1.13

 among

1.12

 here

1.10

 darbu

1.07

顶部

1.06

 receive

1.05

Activations Density 0.059%