INDEX

Explanations

items following "include"

The neuron detects list‐style or bullet‐point content—i.e. short instructional or enumerated items.

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

and

-2.28

 then

-1.78

of

-1.70

this

-1.62

 This

-1.59

ykjav

-1.53

 didn

-1.41

oded

-1.36

&#

-1.29

Legături

-1.29

POSITIVE LOGITS

4.84

2.55

：……

2.47

៖

2.31

：

2.14

 şun

2.13

():

2.11

ઃ

1.96

 seguenti

1.91

 følgende

1.87

Activations Density 0.674%