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

    Neuronpedia

    INDEX
    Explanations

    phrases related to outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to outcomes or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.69
    cious
    -0.65
    uggish
    -0.63
    avin
    -0.61
    erva
    -0.60
    rontal
    -0.57
    rio
    -0.57
     Pry
    -0.57
    auri
    -0.56
     Pse
    -0.56
    POSITIVE LOGITS
    fitting
    0.90
    fitted
    0.89
    icago
    0.84
    wards
    0.71
    flows
    0.68
    posts
    0.68
     agreements
    0.66
     centr
    0.66
     arrangements
    0.66
     how
    0.65
    Act Density 0.033%

    No Known Activations