INDEX

Explanations

having or having not

This neuron is picking up on informal, conversational “discourse markers” or filler phrases (e.g. “what…not,” “let me know,” “here is,” “having…”).

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

 sejam

-0.79

 étaient

-0.78

要想

-0.76

 gewöhnlich

-0.75

这是一个

-0.74

去做

-0.73

eniably

-0.71



-0.71

λλην

-0.71

zeba

-0.69

POSITIVE LOGITS

 having

3.55

 have

3.33

Have

2.84

Having

2.77

 Have

2.59

 Having

2.53

have

2.44

 иметь

2.41

having

2.39

 HAVE

2.19

Activations Density 0.023%