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

    Neuronpedia

    INDEX
    Explanations

    patterns related to names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of names and titles related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BILITIES
    -0.83
    Reviewed
    -0.65
    BILITY
    -0.64
    kefeller
    -0.64
     litter
    -0.63
     canned
    -0.63
     pack
    -0.62
     wit
    -0.62
    acco
    -0.61
    ©¶æ
    -0.61
    POSITIVE LOGITS
     Pradesh
    0.87
    ients
    0.75
    ometown
    0.72
    uddin
    0.71
    undai
    0.71
    asca
    0.71
    oub
    0.71
    hya
    0.70
    amines
    0.66
    oola
    0.65
    Act Density 0.145%

    No Known Activations