INDEX

Explanations

a word or phrase

The neuron fires on individual words that carry strong emphasis or emotional intensity (e.g. hot-button, shocking, sinister, watershed).

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

伱

-1.27

ціона

-1.21

 รถ

-1.21

却被

-1.21

ɸ

-1.20

 AGAIN

-1.20

исленность

-1.20

⢱

-1.17

奬

-1.17

 أوروبا

-1.17

POSITIVE LOGITS

 that

2.00

 there

1.52

not

1.52

 principalmente

1.46

 не

1.42

for

1.41

 nicht

1.31

bbling

1.30

 other

1.27

 \%$\\

1.24

Activations Density 0.053%