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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating personal opinions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intent or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meter
    -0.68
     Router
    -0.63
     Pis
    -0.62
     [+]
    -0.62
    ielding
    -0.60
    ItemTracker
    -0.60
    Links
    -0.60
     Flavoring
    -0.60
    natureconservancy
    -0.60
    catentry
    -0.58
    POSITIVE LOGITS
    ĸļ
    0.80
    icably
    0.73
    ividual
    0.68
    TRY
    0.67
    hyde
    0.66
    ERS
    0.64
     Bradford
    0.64
    erent
    0.63
    FER
    0.62
    initely
    0.62
    Act Density 0.059%

    No Known Activations