INDEX

Explanations

actually

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.53

urlpatterns

-0.52

-0.51

WEBPACK

-0.50

期刊论文

-0.49

ifu

-0.48

ViewFeatures

-0.47

ButterKnife

-0.47

LinkId

-0.46

Referanser

-0.46

POSITIVE LOGITS

<bos>

1.42

Efq

0.74

 itſelf

0.73

 myſelf

0.68

 raiſ

0.67

ſelves

0.67

 themſelves

0.66

цездатний

0.66

ſelf

0.64

 perſon

0.61

Activations Density 0.225%