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

    Neuronpedia

    INDEX
    Explanations

    technical terms and parameters related to configuration settings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    prüche
    -0.57
     esternos
    -0.54
     marinho
    -0.52
     abstrato
    -0.52
    íncia
    -0.52
    phology
    -0.50
     negócios
    -0.50
     stamens
    -0.50
    henswürdigkeiten
    -0.49
    ernalia
    -0.49
    POSITIVE LOGITS
    =$((
    0.68
    UnsafeEnabled
    0.64
    #![
    0.64
    queryInterface
    0.63
    PhysRev
    0.61
    etcode
    0.61
     Wanna
    0.59
    NameInMap
    0.58
    ":{"
    0.58
    ={`${
    0.57
    Act Density 0.065%

    No Known Activations