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

    Neuronpedia

    INDEX
    Explanations

    words related to heat and cooking, specifically focusing on the action of boiling

    oai_token-act-pair · gpt-3.5-turbo

    references to boiling and cooked foods or processes related to heat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournal
    -0.82
    dfx
    -0.81
    alez
    -0.81
    phis
    -0.80
    ngth
    -0.77
    eele
    -0.74
    stood
    -0.73
    edy
    -0.73
     Agency
    -0.72
    rian
    -0.69
    POSITIVE LOGITS
     boiling
    1.15
     boils
    1.09
     boiled
    1.08
     boil
    1.07
     kettle
    1.03
     simmer
    0.89
    SourceFile
    0.77
     stove
    0.75
    hens
    0.73
     arsenic
    0.73
    Act Density 0.012%

    No Known Activations