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

    Neuronpedia

    INDEX
    Explanations

    the name "Barack" with varying levels of activation depending on the context

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those related to politics and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.75
    PsyNetMessage
    -0.75
     eleph
    -0.71
    psons
    -0.70
     occas
    -0.66
     externalToEVAOnly
    -0.66
    undai
    -0.64
     calf
    -0.63
    ORPG
    -0.63
    ervation
    -0.62
    POSITIVE LOGITS
    ery
    1.14
    intosh
    1.13
    enzie
    1.10
    nesses
    1.03
    ings
    0.96
    Berry
    0.95
    luster
    0.95
    ademic
    0.92
    NOW
    0.88
    itude
    0.84
    Act Density 0.019%

    No Known Activations