INDEX

Explanations

modal verbs and knowing/saying

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

𝟐

-1.38

maximize

-1.36

стон

-1.35

🇲

-1.35

 LAKE

-1.30

tison

-1.27

šana

-1.26

endrait

-1.25

 anos

-1.25

ITY

-1.25

POSITIVE LOGITS

how

2.45

 where

1.93

who

1.88

 when

1.67

 decide

1.51

 whether

1.48

 Хотя

1.45

 know

1.43

 knows

1.43

 this

1.42

Activations Density 0.011%