INDEX

Explanations

(

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

 المعيارى

-0.75

 Monfieur

-0.67

 CallOverrides

-0.66

Efq

-0.66

 חיצוניים

-0.66

KommentareTeilen

-0.66

DockStyle

-0.66

ftagPool

-0.65

 Мексичка

-0.64

findpost

-0.63

POSITIVE LOGITS

keV

0.51

NGC

0.46

TeV

0.45

neutron

0.45

isel

0.44

sche

0.42

cosmo

0.41

imshow

0.41

RADIUS

0.41

สัม

0.40

Activations Density 0.012%