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

    Neuronpedia

    INDEX
    Explanations

    concepts related to logic, reason, and rationality

    oai_token-act-pair · gpt-3.5-turbo

    symbols and concepts related to reasoning and abstract ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psons
    -0.68
     confir
    -0.67
    icipated
    -0.67
    ptoms
    -0.65
    BuyableInstoreAndOnline
    -0.63
    leased
    -0.61
    itant
    -0.61
    olulu
    -0.61
    ersen
    -0.60
    IONS
    -0.59
    POSITIVE LOGITS
    ism
    0.80
    ativity
    0.73
    igraph
    0.72
     versus
    0.70
    ismo
    0.70
    ocracy
    0.66
    atism
    0.64
    less
    0.64
    gam
    0.63
    edience
    0.62
    Act Density 0.780%

    No Known Activations