INDEX

Explanations

sounds

The neuron detects onomatopoeic sound words—terms that mimic or evoke noises (e.g. hum, whistle, snore, wheeze, 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

you

-1.93

gik

-1.79

?”

-1.78

ኧ

-1.78

ſu

-1.75

 людей

-1.73

is

-1.73

 absurdo

-1.70

 residuos

-1.64

他の

-1.61

POSITIVE LOGITS

in

2.03

for

1.97

猡

1.83

蟊

1.79

 kekasih

1.59

1.58

 adelant

1.57

directors

1.56

1.55

厯

1.55

Activations Density 0.025%