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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recalling or remembering something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to thoughts or reflections that come to mind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.73
     MSG
    -0.67
     pudding
    -0.65
    aceae
    -0.65
     Auckland
    -0.65
    anooga
    -0.64
     Onion
    -0.63
    nic
    -0.61
     appetite
    -0.61
     cocktail
    -0.60
    POSITIVE LOGITS
    ç«
    0.72
    ONT
    0.71
    ãĤ¼
    0.71
     Mechdragon
    0.69
    NetMessage
    0.68
    urch
    0.68
    ãģ«
    0.67
    姫
    0.66
    éĹ
    0.66
    åĬ
    0.65
    Act Density 0.070%

    No Known Activations