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

    Neuronpedia

    INDEX
    Explanations

    references to chocolate

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atives
    -0.76
    WARD
    -0.75
    umbnail
    -0.71
    kus
    -0.69
    ership
    -0.69
    igate
    -0.69
    inen
    -0.68
     Imran
    -0.67
     Fargo
    -0.66
     plur
    -0.66
    POSITIVE LOGITS
     cake
    0.94
     pudding
    0.91
    anut
    0.90
     chocolate
    0.89
    âĺħâĺħ
    0.85
     coated
    0.82
     bean
    0.81
     chip
    0.80
    ocolate
    0.80
     cane
    0.80
    Act Density 0.014%

    No Known Activations