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

    Neuronpedia

    INDEX
    Explanations

    statistical or numerical information

    oai_token-act-pair · gpt-3.5-turbo

    statistical averages and measures related to various demographics or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bane
    -0.91
    assies
    -0.75
    heid
    -0.72
    Ü
    -0.72
    cit
    -0.71
    perse
    -0.70
    atography
    -0.69
    hiro
    -0.68
    ittees
    -0.68
    burg
    -0.68
    POSITIVE LOGITS
     household
    0.84
     monthly
    0.84
     lifespan
    0.83
     capita
    0.79
     hourly
    0.79
     yearly
    0.78
     annual
    0.76
     homeowner
    0.75
     person
    0.75
     jo
    0.74
    Act Density 0.026%

    No Known Activations