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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Kate" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atio
    -0.80
    ATIONS
    -0.74
     externalToEVAOnly
    -0.69
    ATIVE
    -0.69
    Interstitial
    -0.68
    places
    -0.66
    indal
    -0.66
    ATOR
    -0.64
    iple
    -0.64
    rums
    -0.63
    POSITIVE LOGITS
     Upton
    0.94
     Mara
    0.93
     Wins
    0.92
    vich
    0.86
     Moss
    0.79
    y
    0.79
    fet
    0.78
    patrick
    0.76
     McCann
    0.73
     Bold
    0.73
    Act Density 0.035%

    No Known Activations