INDEX

Explanations

otherwise or contrary

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

謌

-1.59

彼女は

-1.52

相変わらず

-1.47

僕も

-1.47

ごちそう

-1.45

 étan

-1.44

これからの

-1.43

 accél

-1.42

嘖

-1.41

 renfor

-1.40

POSITIVE LOGITS

 before

2.13

 than

1.97

 they

1.93

 when

1.84

if

1.74

[]:

1.64

habited

1.59

";

1.56

átor

1.48

vaded

1.47

Activations Density 0.011%