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

    Neuronpedia

    INDEX
    Explanations

    names of people, with a focus on variations like different spellings or nicknames

    oai_token-act-pair · gpt-3.5-turbo

    references to names, particularly those related to specific individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inement
    -0.90
    aults
    -0.78
    cffff
    -0.77
    urer
    -0.75
    ebus
    -0.74
    eller
    -0.74
    jri
    -0.74
    iership
    -0.74
    olesc
    -0.72
    heed
    -0.72
    POSITIVE LOGITS
    mary
    1.38
    cling
    1.00
    abeth
    0.91
    othy
    0.84
    cles
    0.80
     Niet
    0.80
    apolis
    0.80
    hyde
    0.79
     Stan
    0.77
    colm
    0.77
    Act Density 0.019%

    No Known Activations