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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of names associated with public figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loves
    -0.65
     Travels
    -0.65
    ometimes
    -0.62
     wakes
    -0.60
    wealth
    -0.59
     wealth
    -0.59
    conom
    -0.59
    ggles
    -0.57
    atility
    -0.57
     revolutions
    -0.57
    POSITIVE LOGITS
     requested
    0.76
     objected
    0.73
     licence
    0.72
     citing
    0.71
     bidder
    0.71
     submissions
    0.71
     ineligible
    0.70
     scrut
    0.69
     registrations
    0.68
     submitted
    0.68
    Act Density 1.259%

    No Known Activations