INDEX

Explanations

pronouns followed by verbs

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

hline

-1.47

 étrange

-1.40

 éton

-1.40

 jouets

-1.35

rocław

-1.34

iestety

-1.34

ïc

-1.33

 souten

-1.31

مدل

-1.30

 avut

-1.30

POSITIVE LOGITS

if

1.94

 what

1.88

 would

1.72

<bos>

1.45

 this

1.41

is

1.39

 when

1.38

romatic

1.37

one

1.35

産の

1.34

Activations Density 0.080%