INDEX

Explanations

chess board coordinates

The neuron strongly fires on longer, less common content words (e.g. technical or specialist vocabulary) rather than on short or function words.

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

지

0.89

 Review

0.84

ب

0.82

 Milestone

0.80

Ꭰ

0.78

 Mira

0.78

ات

0.77

 Miracle

0.77

 或者

0.77

 Nice

0.77

POSITIVE LOGITS

FromFile

0.84

aranth

0.79

IDES

0.79

意義

0.79

硣

0.77

 noirâtre

0.76

Penumpang

0.73

ingham

0.73

packageName

0.71

 escolar

0.71

Activations Density 0.000%