INDEX

Explanations

foreign words

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sound

-1.88

sound

-1.86

 Sound

-1.82

 noise

-1.80

 SOUND

-1.79

Sound

-1.77

 Noise

-1.76

noise

-1.72

Noise

-1.66

 sounded

-1.60

POSITIVE LOGITS

 ostavi

0.50

@"/

0.45

 sodio

0.44

glises

0.44

 useParams

0.43

 cubana

0.42

 HasFactory

0.41

viez

0.40

 toothpick

0.40

 Anatom

0.40

Activations Density 0.233%