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

    Neuronpedia

    INDEX
    Explanations

    phrases related to representation

    oai_token-act-pair · gpt-3.5-turbo

    references to representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffe
    -0.77
    lys
    -0.73
    trap
    -0.72
    iar
    -0.69
    linger
    -0.69
    sic
    -0.69
    ffer
    -0.68
    imb
    -0.68
    launch
    -0.68
    show
    -0.67
    POSITIVE LOGITS
    ational
    1.09
    atively
    0.86
    eers
    0.83
    atives
    0.80
     Humanity
    0.79
     constituencies
    0.74
     humanity
    0.74
     minorities
    0.73
    ATIVE
    0.73
     humankind
    0.71
    Act Density 0.046%

    No Known Activations