INDEX

Explanations

familiarity or knowledge

This neuron strongly activates on the word “as” (especially in constructions like “known as” or comparative uses of “as”).

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

 môžete

-1.27

if

-1.25

 hermano

-1.25

acakt

-1.25

Teknik

-1.24

dö

-1.23

in

-1.22

 what

-1.20

 encontrarás

-1.18

してみました

-1.18

POSITIVE LOGITS

1.62

 veliko

1.45

 petrified

1.38

öglich

1.34

 lukewarm

1.32

in

1.31

 cebola

1.29

FARE

1.29

 Manten

1.28

())));

1.27

Activations Density 0.050%