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

    Neuronpedia

    INDEX
    Explanations

    the last names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Lund" and "Riks."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mug
    -0.66
     mug
    -0.65
     Em
    -0.63
     Amb
    -0.63
     contempt
    -0.62
     civil
    -0.62
     appeals
    -0.61
     Beyon
    -0.58
     âĻ
    -0.58
     wake
    -0.58
    POSITIVE LOGITS
    lund
    4.81
    riks
    1.49
    holm
    1.48
    qv
    1.34
    imov
    1.20
     Lund
    1.17
    sson
    1.15
    hoff
    1.13
    gaard
    1.11
    strom
    1.07
    Act Density 0.033%

    No Known Activations