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

    Neuronpedia

    INDEX
    Explanations

    instructions or steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.84
     Osw
    -0.75
    Reviewer
    -0.70
     Norn
    -0.69
    Upgrade
    -0.68
     Odyssey
    -0.66
    tel
    -0.65
    href
    -0.65
     Reincarn
    -0.63
     escort
    -0.63
    POSITIVE LOGITS
     mixture
    1.03
     gelatin
    0.97
     thick
    0.96
     creamy
    0.95
     brown
    0.92
     crust
    0.91
     frag
    0.90
     crispy
    0.89
     translucent
    0.89
     evenly
    0.89
    Act Density 0.078%

    No Known Activations