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

    Neuronpedia

    INDEX
    Explanations

    mentions of Intel Xeon processors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific computer processor models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.97
    ship
    -0.83
    oro
    -0.81
    fur
    -0.78
    mallow
    -0.77
    mented
    -0.75
    inals
    -0.75
    bender
    -0.74
    aldi
    -0.73
    girls
    -0.72
    POSITIVE LOGITS
     lapse
    0.77
    umbers
    0.76
    CVE
    0.75
    ieves
    0.74
    tera
    0.71
    sis
    0.71
    xual
    0.71
    arios
    0.70
    ternal
    0.69
    cible
    0.67
    Act Density 0.038%

    No Known Activations