INDEX

Explanations

large

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

 large

-2.81

large

-2.58

Large

-2.33

 Large

-2.30

 LARGE

-2.06

LARGE

-1.74

 larger

-1.67

 largest

-1.66

 huge

-1.64

larger

-1.55

POSITIVE LOGITS

+:+

0.93

 getopt

0.64

protoimpl

0.63

 igneous

0.62

hearted

0.60

 intestine

0.60

 hearted

0.58

EndGlobalSection

0.58

RTLD

0.58

ImageContext

0.57

Activations Density 0.249%