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

    Neuronpedia

    INDEX
    Explanations

    phrases or names related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of people or entities, particularly in a publishing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akin
    -0.73
    ascript
    -0.66
     adolesc
    -0.65
     pains
    -0.65
     mornings
    -0.60
    olor
    -0.60
    abase
    -0.60
    itably
    -0.60
     acquisitions
    -0.58
     deceptive
    -0.58
    POSITIVE LOGITS
    ophy
    0.79
    kov
    0.66
    aviour
    0.65
    iazep
    0.64
    Ĥ¬
    0.64
    pad
    0.64
    oshenko
    0.64
    drm
    0.62
    zag
    0.61
    ç«
    0.61
    Act Density 0.204%

    No Known Activations