INDEX

Explanations

quick and fast

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

IBILITIES

-0.77

 esforço

-0.77

 Wrestle

-0.76

 indicó

-0.76

 Vorstellungen

-0.74

щую

-0.73

Stret

-0.73

reciate

-0.72

 něko

-0.72

(`

-0.71

POSITIVE LOGITS

 paced

1.28

paced

0.96

 moving

0.88

 uptake

0.88

 fast

0.87

on

0.84

 learners

0.82

 thinking

0.80

moving

0.77

 footed

0.77

Activations Density 0.015%