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

    Neuronpedia

    INDEX
    Explanations

    mentions of food ingredients and unhealthy dietary components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wireType
    -0.52
    OCCURRED
    -0.49
    TabbedPane
    -0.45
     localVar
    -0.45
    errHandler
    -0.44
     unknownFields
    -0.43
    critto
    -0.42
    GrantedAuthority
    -0.42
    ImageContext
    -0.41
    onActivityResult
    -0.40
    POSITIVE LOGITS
     artificial
    1.17
    artificial
    0.94
     Artificial
    0.94
     synthetic
    0.92
    Artificial
    0.91
     preservatives
    0.90
     künst
    0.88
     artific
    0.84
     chemicals
    0.84
     chemical
    0.82
    Act Density 0.290%

    No Known Activations