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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of high-quality items or products

    oai_token-act-pair · gpt-3.5-turbo

    references to high-quality products or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.75
    kens
    -0.75
    sie
    -0.69
    ften
    -0.68
    chy
    -0.68
    osphere
    -0.65
    thur
    -0.65
     Hanson
    -0.64
    sylv
    -0.64
    Marie
    -0.64
    POSITIVE LOGITS
     assurance
    1.05
     quality
    1.02
    Quality
    0.84
     Quality
    0.79
    quality
    0.77
    umenthal
    0.77
    smanship
    0.77
     choices
    0.76
     output
    0.75
     alternatives
    0.75
    Act Density 0.017%

    No Known Activations