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

    Neuronpedia

    INDEX
    Explanations

    references to electronic device models, such as specifications and prices

    oai_token-act-pair · gpt-3.5-turbo

    references to different models of a specific product

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.91
    vernment
    -0.90
    ulhu
    -0.85
    usters
    -0.84
    olulu
    -0.83
    estern
    -0.83
    ĵĺ
    -0.82
    cffff
    -0.80
    olkien
    -0.79
    agnar
    -0.77
    POSITIVE LOGITS
    Versions
    0.90
     models
    0.89
    model
    0.85
     model
    0.78
     BMW
    0.75
     versions
    0.72
    models
    0.70
     Models
    0.70
     incarnation
    0.70
     Mayhem
    0.69
    Act Density 0.017%

    No Known Activations