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

    Neuronpedia

    INDEX
    Explanations

    names of individuals involved in various news stories

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maria
    -0.77
    į
    -0.73
    ference
    -0.67
    Els
    -0.67
    uate
    -0.65
    LR
    -0.63
    cp
    -0.62
    cknowled
    -0.62
    Laura
    -0.61
    omatic
    -0.60
    POSITIVE LOGITS
     Sr
    0.89
    ovich
    0.81
     Jr
    0.79
    enegger
    0.78
     III
    0.74
     QC
    0.72
     campaigned
    0.69
     imperson
    0.69
    agher
    0.68
     uttered
    0.66
    Act Density 0.132%

    No Known Activations