INDEX

Explanations

exposure

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

 exposure

-2.47

 Exposure

-2.38

exposure

-2.34

Exposure

-2.31

exposed

-2.13

 exposed

-2.13

 EXPOSURE

-2.11

 expose

-2.05

 Exposed

-1.98

 exposing

-1.96

POSITIVE LOGITS

msgTypes

0.66

ymce

0.64

kháu

0.57

WriteBarrier

0.54

TextChanged

0.52

 nectar

0.51

 يتيمه

0.50

 diphtheria

0.49

 penguin

0.48

FormUrlEncoded

0.48

Activations Density 0.322%