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

    Neuronpedia

    INDEX
    Explanations

    references to Western culture and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InSection
    -0.59
     braun
    -0.56
    قل
    -0.52
    iren
    -0.49
     budgeting
    -0.49
    หวัด
    -0.49
    ires
    -0.49
     transfieras
    -0.49
    Suara
    -0.49
     oportunidade
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.88
     anglo
    0.70
    Anglo
    0.68
    ędzynarod
    0.68
     English
    0.65
    영어
    0.64
    ValueStyle
    0.64
    estero
    0.63
    AnchorStyles
    0.63
     Anglo
    0.62
    Act Density 0.294%

    No Known Activations