INDEX

Explanations

he followed by verbs

The neuron is primarily triggered by past‐tense verbs describing actions (e.g. wrote, recorded, co‐founded, produced, held, left).

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

 każdego

-1.43

岀

-1.38

 Brunnen

-1.37

 Deixe

-1.35

 توانند

-1.34

描く

-1.34

genheiten

-1.33

 jednego

-1.27

רְ

-1.26

 aliviar

-1.26

POSITIVE LOGITS

on

1.59

and

1.57

own

1.46

 with

1.46

 البته

1.40

1.38

the

1.37

 трех

1.26

 vermel

1.25

for

1.24

Activations Density 0.037%