INDEX

Explanations

stimulation

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

 smash

-0.45

andReturn

-0.44

 Amon

-0.42

 nailed

-0.41

Gfx

-0.40

τικός

-0.40

Chill

-0.40

OrUpdate

-0.39

 perse

-0.39

le

-0.38

POSITIVE LOGITS

<bos>

0.78

fillType

0.74

modelBuilder

0.71

SequentialGroup

0.70

twimg

0.69

المناصب

0.66

]")]

0.65

 autorytatywna

0.63

下载附件

0.62

 pinulongan

0.59

Activations Density 0.027%