INDEX

Explanations

operations

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

 activities

-1.55

 operations

-1.47

 functions

-1.31

activities

-1.25

operations

-1.13

 services

-1.11

 affairs

-1.10

 Activities

-1.08

 functionalities

-1.06

 processes

-1.05

POSITIVE LOGITS

 that

0.69

 like

0.68

0.61

 such

0.60

0.56

 larmes

0.49

in

0.47

for

0.47

 épaules

0.46

 soñar

0.45

Activations Density 0.099%