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

    Neuronpedia

    INDEX
    Explanations

    proper names related to businesses or places

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.87
     skelet
    -0.73
     tempo
    -0.67
    ails
    -0.66
     rehearsal
    -0.65
    ives
    -0.65
    ocks
    -0.64
    uary
    -0.62
    swick
    -0.62
    robe
    -0.62
    POSITIVE LOGITS
    atu
    0.77
     Holden
    0.73
    Ń·
    0.72
    utral
    0.72
     cir
    0.71
     Britann
    0.70
     chau
    0.70
    arth
    0.70
    biz
    0.69
    )=(
    0.69
    Act Density 0.037%

    No Known Activations