Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to programming or technical functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Segoe
    -0.72
     allude
    -0.64
     podob
    -0.62
    ப்பட்ட
    -0.60
     @}
    -0.58
     chodzi
    -0.58
    Tito
    -0.58
    blocked
    -0.57
    至此
    -0.57
     Bassi
    -0.57
    POSITIVE LOGITS
    InjectAttribute
    0.73
    Ανα
    0.69
     inflater
    0.68
     vastaan
    0.67
    ViewFeatures
    0.67
     megsz
    0.66
    身を
    0.65
    Rec
    0.65
     įsi
    0.65
    Рас
    0.64
    Act Density 0.622%

    No Known Activations