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

    Neuronpedia

    INDEX
    Explanations

    comparative relationships or similarities

    oai_token-act-pair · gpt-3.5-turbo

    references to comparability or comparisons between different entities or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spe
    -0.85
    haw
    -0.72
    asel
    -0.70
    nen
    -0.69
    ward
    -0.69
    liner
    -0.68
    zyme
    -0.68
    mail
    -0.68
    dot
    -0.67
    wheel
    -0.66
    POSITIVE LOGITS
    MpServer
    0.93
     sized
    0.92
     comparisons
    0.89
     favorably
    0.86
     compar
    0.84
     comparable
    0.82
     apples
    0.81
     amounts
    0.80
    isons
    0.79
    lihood
    0.75
    Act Density 0.014%

    No Known Activations