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

    Neuronpedia

    INDEX
    Explanations

    words related to creating or establishing something

    oai_token-act-pair · gpt-3.5-turbo

    instances where something is being formed or established

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reprint
    -0.72
    avoid
    -0.72
    mong
    -0.70
    icals
    -0.68
     renew
    -0.68
    gery
    -0.68
     foresee
    -0.68
     ignite
    -0.67
    onda
    -0.66
    isSpecialOrderable
    -0.65
    POSITIVE LOGITS
     nucleus
    0.82
     basis
    0.79
     perimeter
    0.71
    IU
    0.70
    Interstitial
    0.70
     makeshift
    0.69
     backbone
    0.69
    Ul
    0.68
    -+-+
    0.67
    DragonMagazine
    0.66
    Act Density 0.117%

    No Known Activations