INDEX

Explanations

dialogue prompt examples

The neuron strongly activates on tokens that begin new paragraphs (i.e. tokens appearing immediately after blank‐line or document boundaries).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

बाग

0.67

(!)

0.64

跻

0.60

0.59

(!)

0.58

Así

0.56

den

0.55

POSITIVE LOGITS

 nums

0.75

 FontSize

0.68

 vertices

0.68

 plugins

0.66

 inodes

0.66

 함수

0.65

 scanf

0.64

 embeddings

0.64

phd

0.64

 theorems

0.63

Activations Density 3.345%