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

    Neuronpedia

    INDEX
    Explanations

    words related to making comparisons between different entities or concepts, particularly in a way that implies similarity or difference

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that draw parallels between different subjects, particularly those involving historical or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alde
    -0.67
    iol
    -0.67
    ategor
    -0.65
    oji
    -0.65
    iband
    -0.64
    aligned
    -0.63
    ainer
    -0.62
    wind
    -0.62
    alloc
    -0.62
    itive
    -0.61
    POSITIVE LOGITS
     ours
    0.83
    soDeliveryDate
    0.79
     theirs
    0.74
     slavery
    0.72
     Dickens
    0.72
     counterparts
    0.71
     brill
    0.70
     Adolf
    0.69
     lyn
    0.69
     contemporaries
    0.68
    Act Density 0.125%

    No Known Activations