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

    Neuronpedia

    INDEX
    Explanations

    references to cereal boxes

    oai_token-act-pair · gpt-3.5-turbo

    references to cereal and related food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sein
    -0.81
    etter
    -0.77
    handled
    -0.75
    angs
    -0.72
    essing
    -0.70
     tremend
    -0.68
    ĺħ
    -0.68
    liness
    -0.68
    fully
    -0.67
    finding
    -0.67
    POSITIVE LOGITS
     Stout
    0.76
    alore
    0.76
     NAD
    0.75
    mil
    0.73
    FACE
    0.73
    llo
    0.72
     Milk
    0.72
     cere
    0.71
    AAF
    0.71
     milk
    0.70
    Act Density 0.045%

    No Known Activations