INDEX

Explanations

according to

The neuron detects occurrences of the word “according,” especially in the phrase “according to.”

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

idlertid

-2.34

朏

-2.34

 dwóch

-2.30

 綺麗

-2.23

 VERY

-2.16

who

-2.06

 senza

-2.02

の良い

-2.02

に行って

-2.00

POSITIVE LOGITS

蕯

3.05

࣭

3.05

 Perhaps

2.83

 However

2.59

 bukanlah

2.50

 artistico

2.50

 Additionally

2.47

 Maybe

2.47

 Regardless

2.45

地在

2.45

Activations Density 0.016%