INDEX

Explanations

No Explanations Found

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

oldo

-0.87

 Tack

-0.82

眶

-0.72

 Numer

-0.72

社の

-0.71

遭遇

-0.69

SCRIP

-0.69

 Valor

-0.68

を経て

-0.68

Toponymie

-0.67

POSITIVE LOGITS

sub

1.29

 submenu

1.27

SubMenu

1.21

 mega

1.13

Sub

1.12

 Mega

1.07

submenu

1.07

 getSub

1.05

Sub

1.00

setLevel

0.99

Activations Density 0.038%

No Known Activations