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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals, particularly in political or public roles

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, particularly in political and cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Antar
    -0.86
    ophon
    -0.75
    ocard
    -0.72
    ocre
    -0.70
     Pearce
    -0.68
     Avalon
    -0.68
     utility
    -0.66
    annis
    -0.65
    erville
    -0.64
     Phant
    -0.64
    POSITIVE LOGITS
     DeVos
    1.07
    etsy
    0.90
    agall
    0.81
    enic
    0.80
    lisher
    0.78
    lain
    0.74
    heimer
    0.73
    ãĥīãĥ©
    0.72
    cot
    0.71
    habi
    0.71
    Act Density 0.024%

    No Known Activations