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

    Neuronpedia

    INDEX
    Explanations

    words related to culinary spices, particularly focused on 'spice'

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of spices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Turing
    -0.82
    escription
    -0.78
    apixel
    -0.77
    iscopal
    -0.76
    izoph
    -0.74
    cedented
    -0.73
    ffen
    -0.72
    ufact
    -0.69
    sembly
    -0.69
    avering
    -0.67
    POSITIVE LOGITS
     spice
    1.16
     spices
    1.02
     powd
    0.93
     blends
    0.91
     Flavoring
    0.85
     Spice
    0.84
    Jet
    0.82
     aroma
    0.78
     blend
    0.78
     powder
    0.77
    Act Density 0.021%

    No Known Activations