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

    Neuronpedia

    INDEX
    Explanations

    proper nouns relating to a specific person, potentially a public figure

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Steve Jobs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.74
    miss
    -0.71
    emporary
    -0.69
    graduate
    -0.67
    catch
    -0.64
     Georgian
    -0.63
    acting
    -0.63
    ritch
    -0.62
    arity
    -0.62
     Dominican
    -0.61
    POSITIVE LOGITS
     Jobs
    0.95
     Maker
    0.81
    oint
    0.77
    ovie
    0.76
    ullivan
    0.76
    pring
    0.75
    ython
    0.75
     Simulator
    0.74
    _>
    0.73
     Pax
    0.73
    Act Density 0.013%

    No Known Activations