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

    Neuronpedia

    INDEX
    Explanations

    recommendations or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to recommendations or endorsements of products, services, or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bom
    -0.63
    hatt
    -0.63
    bert
    -0.63
    chan
    -0.62
    catentry
    -0.62
    kered
    -0.62
    von
    -0.62
    sen
    -0.62
     Ern
    -0.61
     NTS
    -0.60
    POSITIVE LOGITS
    Recommend
    0.85
    ENDED
    0.74
    recomm
    0.73
     recommending
    0.72
    ournals
    0.72
    avorite
    0.70
    Recommended
    0.67
     downloading
    0.67
     Recommended
    0.66
    agnar
    0.63
    Act Density 0.039%

    No Known Activations