INDEX

Explanations

someone telling someone

The neuron flags direct requests for information—that is, “someone please tell me,” “tell me,” “can you tell me,” etc.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 любой

-1.62

圌

-1.34

ximos

-1.34

didn

-1.34

憷

-1.28

 également

-1.25

 alguns

-1.24

gerie

-1.24

鸶

-1.23

punkten

-1.20

POSITIVE LOGITS

 this

1.95

 because

1.91

 when

1.81

at

1.60

by

1.57

 these

1.52

 before

1.47

two

1.47

 from

1.45

if

1.41

Activations Density 0.040%