INDEX

Explanations

Advertisement or Q following

The neuron detects “ADVERTISEMENT” markers (i.e. ad‐break labels) in the text.

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

who

-1.75

罴

-1.69

for

-1.66

 rainha

-1.57

so

-1.53

铼

-1.53

了很多

-1.48

 where

-1.47

ৄ

-1.47

佉

-1.45

POSITIVE LOGITS

梛

1.69

 chanteuse

1.52

或者

1.47

 یا

1.47

</strong>

1.45

 appétit

1.45

ーーーー

1.44

 или

1.42

䊳

1.42

孩子们

1.41

Activations Density 0.001%