INDEX

Explanations

specific

This neuron detects the openings of square‐bracketed parenthetical or asides (i.e. the “\[” token and the content immediately following it).

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

 ちょっと

0.70

 นิด

0.68

 ไม่มี

0.67

 VALUE

0.65

>";

0.64

0.63

 こんな

0.62

 ชีวิต

0.61

 WILL

0.61

+,

0.60

POSITIVE LOGITS

,]

0.66

sic

0.64

laughs

0.63

الية

0.60

…。

0.60

Laugh

0.59

фіка

0.58

。[

0.57

.]

0.57

:]

0.57

Activations Density 0.012%