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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, especially their first names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.66
    emale
    -0.62
     undermin
    -0.54
    ../
    -0.53
    chnology
    -0.52
    ãĥ¼ãĥĨ
    -0.52
    ntil
    -0.52
    milo
    -0.52
    arettes
    -0.51
    shapeshifter
    -0.51
    POSITIVE LOGITS
     Reed
    0.71
     Rice
    0.68
     Alexander
    0.68
     Roberts
    0.68
     Wright
    0.66
     Foster
    0.65
     Jenkins
    0.65
     Patrick
    0.65
     Clarke
    0.65
     Butler
    0.64
    Act Density 0.393%

    No Known Activations