INDEX

Explanations

names starting with 'Ay' or 'Ab'

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

 Förder

-0.85

一座

-0.82

 uneasy

-0.76

AV

-0.75

 ellen

-0.75

しかも

-0.74

iget

-0.74

uvo

-0.72

 notific

-0.72

AL

-0.72

POSITIVE LOGITS

atleta

0.85

 héri

0.77

 youre

0.77

 sogni

0.75

 olvidado

0.74

 recogni

0.74

Vb

0.73

Gön

0.73

 submar

0.73

Airplane

0.73

Activations Density 0.045%