INDEX

Explanations

named entities and their states

This neuron activates on capitalized technical terms and acronyms (e.g., SVG, AI, CAM, CJD, ACS, COPD, SPR, PowerPoint) indicating it’s detecting domain-specific named entities.

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

多かった

-1.46

 voltak

-1.39

)=>{

-1.33

ходили

-1.33

になるので

-1.29

 vannak

-1.28

cuz

-1.27

^{*},

-1.26

 magnifiques

-1.25

になってしまう

-1.25

POSITIVE LOGITS

is

3.95

has

2.58

isn

2.30

was

2.22

can

2.14

 wasn

1.84

 itself

1.83

 shouldn

1.71

 generally

1.67

 cannot

1.66

Activations Density 0.404%