INDEX

Explanations

metric prefixes for large quantities

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

apsed

-0.82

all

-0.81

 Zeit

-0.78

된

-0.77

but

-0.74

 porcentaje

-0.73

 unlocks

-0.71

galus

-0.70

 expresión

-0.69

hemat

-0.69

POSITIVE LOGITS

সং

0.92

ilion

0.92

 Artifact

0.91

illion

0.91

bytes

0.90

Ohm

0.90

 higien

0.86

Bytes

0.85

itre

0.84

 eksklu

0.82

Activations Density 0.027%