INDEX

Explanations

from a source

The neuron strongly activates on the preposition “from,” i.e. it detects occurrences of the word “from.”

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

 prioriti

-1.48

’，

-1.47

 caminh

-1.37

’

-1.37

<bos>

-1.31

 surgiu

-1.31

 consegui

-1.29

-1.28

 tilbud

-1.27

紧紧

-1.26

POSITIVE LOGITS

 nawet

2.14

by

2.03

him

1.84

 даже

1.77

you

1.73

]$.

1.72

 admiring

1.64

可不是

1.63

 обычно

1.59

 afectadas

1.59

Activations Density 0.015%