INDEX

Explanations

Davies, Davison, Dennison

The neuron strongly activates on occurrences of the substring "Dav"—in particular proper names like Davies, Davidson, Dennison, etc.

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

 или

-2.97

 eerie

-2.56

 второй

-2.47

 ache

-2.45

 glaubt

-2.44

</b>

-2.39

 nuova

-2.38

ৢ

-2.34

麁

-2.33

 oder

-2.31

POSITIVE LOGITS

鹮

3.11

螄

2.52

 放題

2.48

朥

2.48

 russ

2.39

 花纹

2.38

жуть

2.33

!';

2.28

 cristo

2.27

Activations Density 0.005%