INDEX

Explanations

technical issues and policy

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 houſe

-0.69

 purpoſe

-0.69

 myſelf

-0.66

 pleaſure

-0.65

 Monfieur

-0.58

Efq

-0.57

 ſmall

-0.56

 greateſt

-0.55

 ſever

-0.54

 reaſon

-0.53

POSITIVE LOGITS

发表于

0.54

0.49

He

0.48

...

0.48

Lif

0.47

fo

0.47

...

0.47

th

0.45

Res

0.45

We

0.44

Activations Density 0.000%