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

    Neuronpedia

    INDEX
    Explanations

    references to electronic devices or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to electronic items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.82
     Parables
    -0.76
    hig
    -0.73
    cific
    -0.72
    aird
    -0.71
    heimer
    -0.69
    erest
    -0.69
    atar
    -0.69
    arte
    -0.69
    hoff
    -0.69
    POSITIVE LOGITS
     gadgets
    0.93
    ronic
    0.88
     warfare
    0.87
     cigarettes
    0.84
     circuits
    0.81
     electronic
    0.81
     surveillance
    0.78
     gadget
    0.78
     systems
    0.77
     cigarette
    0.76
    Act Density 0.012%

    No Known Activations